Remote Sensing

24 pages, 2879 KB

Open AccessEditor’s ChoiceArticle

A Frequency Attention-Enhanced Network for Semantic Segmentation of High-Resolution Remote Sensing Images

by Jianyi Zhong, Tao Zeng, Zhennan Xu, Caifeng Wu, Shangtuo Qian, Nan Xu, Ziqi Chen, Xin Lyu and Xin Li

Remote Sens. 2025, 17(3), 402; https://doi.org/10.3390/rs17030402 - 24 Jan 2025

Cited by 18 | Viewed by 5423

Abstract

Semantic segmentation of high-resolution remote sensing images (HRRSIs) presents unique challenges due to the intricate spatial and spectral characteristics of these images. Traditional methods often prioritize spatial information while underutilizing the rich spectral context, leading to limited feature discrimination capabilities. To address these [...] Read more.

Semantic segmentation of high-resolution remote sensing images (HRRSIs) presents unique challenges due to the intricate spatial and spectral characteristics of these images. Traditional methods often prioritize spatial information while underutilizing the rich spectral context, leading to limited feature discrimination capabilities. To address these issues, we propose a novel frequency attention-enhanced network (FAENet), which incorporates a frequency attention model (FreqA) to jointly model spectral and spatial contexts. FreqA leverages discrete wavelet transformation (DWT) to decompose input images into distinct frequency components, followed by a two-stage attention mechanism comprising inner-component channel attention (ICCA) and cross-component channel attention (CCCA). These mechanisms enhance spectral representation, which is further refined through a self-attention (SA) module to capture long-range dependencies before transforming back into the spatial domain. FAENet’s encoder–decoder architecture facilitates multiscale feature refinement, enabling effective segmentation. Extensive experiments on the ISPRS Potsdam and LoveDA benchmarks demonstrate that FAENet outperforms state-of-the-art models, achieving superior segmentation accuracy. Ablation studies further validate the contributions of ICCA and CCCA. Moreover, efficiency comparisons confirm the superiority of the proposed FAENet over other models. Full article

(This article belongs to the Special Issue Multi-Task Remote Sensing Image Analysis: Classification, Segmentation, and Change Detection)

► Show Figures

Figure 1

21 pages, 8197 KB

Open AccessEditor’s ChoiceArticle

Quantifying the Impact of Crude Oil Spills on the Mangrove Ecosystem in the Niger Delta Using AI and Earth Observation

by Jemima O’Farrell, Dualta O’Fionnagáin, Abosede Omowumi Babatunde, Micheal Geever, Patricia Codyre, Pearse C. Murphy, Charles Spillane and Aaron Golden

Remote Sens. 2025, 17(3), 358; https://doi.org/10.3390/rs17030358 - 22 Jan 2025

Cited by 17 | Viewed by 11085

Abstract

The extraction, processing and transport of crude oil in the Niger Delta region of Nigeria has long been associated with collateral environmental damage to the largest mangrove ecosystem in Africa. Oil pollution is impacting not only one of the planet’s most ecologically diverse [...] Read more.

The extraction, processing and transport of crude oil in the Niger Delta region of Nigeria has long been associated with collateral environmental damage to the largest mangrove ecosystem in Africa. Oil pollution is impacting not only one of the planet’s most ecologically diverse regions but also the health, livelihoods, and social cohesion of the Delta region inhabitants. Quantifying and directly associating localised oil pollution events to specific petrochemical infrastructure is complicated by the difficulty of monitoring such vast and complex terrain, with documented concerns regarding the thoroughness and impartiality of reported oil pollution events. Earth Observation (EO) offers a means to deliver such a monitoring and assessment capability using Normalised Difference Vegetation Index (NDVI) measurements as a proxy for mangrove biomass health. However, the utility of EO can be impacted by persistent cloud cover in such regions. To overcome such challenges here, we present a workflow that leverages EO-derived high-resolution (10 m) synthetic aperture radar data from the Sentinel-1 satellite constellation combined with machine learning to conduct observations of the spatial land cover changes associated with oil pollution-induced mangrove mortality proximal to pipeline networks in a 9000 km² region of Rivers State located near Port Harcourt. Our analysis identified significant deforestation from 2016–2024, with an estimated mangrove mortality rate of 5644 hectares/year. Using our empirically derived Pipeline Impact Indicator (PII), we mapped the oil pipeline network to 1 km resolution, highlighting specific pipeline locations in need of immediate intervention and restoration, and identified several new pipeline sites showing evidence of significant oil spill damage that have yet to be formally reported. Our findings emphasise the critical need for the continuous and comprehensive monitoring of oil extractive regions using satellite remote sensing to support decision-making and policies to mitigate environmental and societal damage from pipeline oil spills, particularly in ecologically vulnerable regions such as the Niger Delta. Full article

(This article belongs to the Special Issue Remote Sensing for Oil and Gas Development, Production and Monitoring)

► Show Figures

Figure 1

19 pages, 21587 KB

Open AccessEditor’s ChoiceArticle

LocaLock: Enhancing Multi-Object Tracking in Satellite Videos via Local Feature Matching

by Lingyu Kong, Zhiyuan Yan, Hanru Shi, Ting Zhang and Lei Wang

Remote Sens. 2025, 17(3), 371; https://doi.org/10.3390/rs17030371 - 22 Jan 2025

Cited by 7 | Viewed by 3413

Abstract

Multi-object tracking (MOT) in satellite videos is a challenging task due to the small size and blurry features of objects, which often lead to intermittent detection and tracking instability. Many existing object detection and tracking models often struggle with these issues, as they [...] Read more.

Multi-object tracking (MOT) in satellite videos is a challenging task due to the small size and blurry features of objects, which often lead to intermittent detection and tracking instability. Many existing object detection and tracking models often struggle with these issues, as they are not designed to effectively handle the unique characteristics of satellite videos. To address these challenges, we propose LocaLock, a joint detection and tracking framework for MOT that incorporates feature matching concepts from single object tracking (SOT) to enhance tracking stability and reduce intermittent tracking results. Specifically, LocaLock utilizes an anchor-free detection backbone for efficiency and employs a local cost volume (LCV) module to perform precise feature matching in the local area. This provides valuable object priors to the detection head, enabling the model to “lock” onto objects with greater accuracy and mitigate the instability associated with small object detection. Additionally, the local computation within the LCV module ensures low computational complexity and memory usage. Furthermore, LocaLock incorporates a novel motion flow (MoF) module to accumulate and exploit temporal information, further enhancing feature robustness and consistency across frames. Rigorous evaluations on the VISO dataset demonstrate the superior performance of LocaLock, surpassing existing methods in tracking accuracy and precision within the demanding satellite video analysis domain. Notably, LocaLock achieved state-of-the-art performance on the VISO benchmark, achieving a multi-object tracking accuracy (MOTA) of 62.6 while ensuring fast running speed. Full article

(This article belongs to the Special Issue Object Detection and Information Extraction Based on Remote Sensing Imagery (Second Edition))

► Show Figures

Figure 1

26 pages, 7355 KB

Open AccessEditor’s ChoiceArticle

An Enhanced Sequential ISAR Image Scatterer Trajectory Association Method Utilizing Modified Label Gaussian Mixture Probability Hypothesis Density Filter

by Lei Liu, Zuobang Zhou, Cheng Li and Feng Zhou

Remote Sens. 2025, 17(3), 354; https://doi.org/10.3390/rs17030354 - 21 Jan 2025

Cited by 8 | Viewed by 1922

Abstract

In the context of 3D geometric reconstruction from sequential inverse synthetic aperture radar (ISAR) images, the accurate scatterer trajectory association is a critical step. Aiming at the above problem, an enhanced scatterer trajectory association method is proposed by designing a modified label Gaussian [...] Read more.

In the context of 3D geometric reconstruction from sequential inverse synthetic aperture radar (ISAR) images, the accurate scatterer trajectory association is a critical step. Aiming at the above problem, an enhanced scatterer trajectory association method is proposed by designing a modified label Gaussian mixture probability hypothesis density (ML-GM-PHD) filtering algorithm. The algorithm commences by constructing a general motion model for scatterers across sequential ISAR images, followed by an in-depth analysis of their motion characteristics. Subsequently, the actual projected positions and measurements of the scattering centers of the observed target are treated as random finite sets, which allows us to reformulate the scatterer trajectory association into a maximum a posteriori (MAP) estimation problem. After that, a ML-GM-PHD filtering algorithm is proposed to realize the scatterer trajectory association. Furthermore, the proposed method is applied to ISAR images in both the forward and reverse directions, enabling the fusion of trajectories from opposing directions to bolster the completeness of the scatterer trajectories. Finally, the factorization method is performed on the scatterer trajectory matrix to implement the 3D geometry reconstruction of the scattering centers in the observed target. Experimental results based on random points and electromagnetic data verify the effectiveness and performance priority of the proposed algorithm. Full article

(This article belongs to the Special Issue Image Processing and Analysis: Trends in Registration, Data Fusion, 3D Reconstruction, and Change Detection (Third Edition))

► Show Figures

Graphical abstract

19 pages, 7245 KB

Open AccessEditor’s ChoiceArticle

Integrating Drone Truthing and Functional Classification of Remote Sensing Time Series for Supervised Vegetation Mapping

by Giacomo Quattrini, Simone Pesaresi, Nicole Hofmann, Adriano Mancini and Simona Casavecchia

Remote Sens. 2025, 17(2), 330; https://doi.org/10.3390/rs17020330 - 18 Jan 2025

Cited by 7 | Viewed by 4185

Abstract

Accurate vegetation mapping is essential for monitoring biodiversity and managing habitats, particularly in the context of increasing environmental pressures and conservation needs. Ground truthing plays a crucial role in ensuring the accuracy of supervised remote sensing maps, as it provides the high-quality reference [...] Read more.

Accurate vegetation mapping is essential for monitoring biodiversity and managing habitats, particularly in the context of increasing environmental pressures and conservation needs. Ground truthing plays a crucial role in ensuring the accuracy of supervised remote sensing maps, as it provides the high-quality reference data needed for model training and validation. However, traditional ground truthing methods are labor-intensive, time-consuming and restricted in spatial coverage, posing challenges for large-scale or complex landscapes. The advent of drone technology offers an efficient and cost-effective solution to these limitations, enabling the rapid collection of high-resolution imagery even in remote or inaccessible areas. This study proposes an approach to enhance the efficiency of supervised vegetation mapping in complex landscapes, integrating Multivariate Functional Principal Component Analysis (MFPCA) applied to the Sentinel-2 time series with drone-based ground truthing. Unlike traditional ground truthing activities, drone truthing enabled the generation of large, spatially balanced reference datasets, which are critical for machine learning classification systems. These datasets improved classification accuracy by ensuring a comprehensive representation of vegetation spectral variability, enabling the classifier to identify the key phenological patterns that best characterize and distinguish different vegetation types across the landscape. The proposed methodology achieves a classification accuracy of 92.59%, significantly exceeding the commonly reported thresholds for habitat mapping. This approach, characterized by its efficiency, repeatability and adaptability, aligns seamlessly with key environmental monitoring and conservation policies, such as the Habitats Directive. By integrating advanced remote sensing with drone-based technologies, it offers a scalable and cost-effective solution to the challenges of biodiversity monitoring, enabling timely updates and supporting effective habitat management in diverse and complex environments. Full article

(This article belongs to the Special Issue Monitoring and Managing Environmental Sustainability Using Remote Sensing)

► Show Figures

Graphical abstract

32 pages, 14893 KB

Open AccessEditor’s ChoiceArticle

Remote Mapping of Bedrock for Future Cosmogenic Nuclide Exposure Dating Studies in Unvisited Areas of Antarctica

by Jonathan R. Adams, Philippa J. Mason, Stephen J. Roberts, Dylan H. Rood, John L. Smellie, Keir A. Nichols, John Woodward and Joanne S. Johnson

Remote Sens. 2025, 17(2), 314; https://doi.org/10.3390/rs17020314 - 17 Jan 2025

Cited by 3 | Viewed by 3486

Abstract

Cosmogenic nuclide exposure dating is an important technique for reconstructing glacial histories. Many of the most commonly applied cosmogenic nuclides are extracted from the mineral quartz, meaning sampling of felsic (silica-rich) rock is often preferred to sampling of mafic (silica-poor) rock for exposure [...] Read more.

Cosmogenic nuclide exposure dating is an important technique for reconstructing glacial histories. Many of the most commonly applied cosmogenic nuclides are extracted from the mineral quartz, meaning sampling of felsic (silica-rich) rock is often preferred to sampling of mafic (silica-poor) rock for exposure dating studies. Fieldwork in remote regions such as Antarctica is subject to time constraints and considerable logistical challenges, making efficient sample recovery critical to successful research efforts. Remote sensing offers an effective way to map the geology of large areas prior to fieldwork and expedite the sampling process. In this study, we assess the viability of multispectral remote sensing to distinguish felsic from mafic rock outcrops at visible-near infrared (VNIR) and shortwave infrared (SWIR) wavelengths using both the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and very high-resolution Worldview-3 (WV-3) imagery. We applied a combination of spectral mapping and ground truth from spectral measurements of 17 rock samples from Mount Murphy in the Amundsen Sea sector of West Antarctica. Using this approach, we identified four dominant rock types which we used as a basis for felsic–mafic differentiation: felsic granites and gneisses, and mafic basalts and fragmental hydrovolcanic rocks. Supervised classification results indicate WV-3 performs well at differentiating felsic and mafic rock types and that ASTER, while coarser, could also achieve satisfactory results and be used in concert with more targeted WV-3 image acquisitions. Finally, we present a revised felsic–mafic geological map for Mt Murphy. Overall, our results highlight the potential of spectral mapping for preliminary reconnaissance when planning future cosmogenic nuclide sampling campaigns in remote, unvisited areas of the polar regions. Full article

(This article belongs to the Special Issue Antarctic Remote Sensing Applications (Second Edition))

► Show Figures

Figure 1

32 pages, 6342 KB

Open AccessEditor’s ChoiceArticle

Statewide Forest Canopy Cover Mapping of Florida Using Synergistic Integration of Spaceborne LiDAR, SAR, and Optical Imagery

by Monique Bohora Schlickmann, Inacio Thomaz Bueno, Denis Valle, William M. Hammond, Susan J. Prichard, Andrew T. Hudak, Carine Klauberg, Mauro Alessandro Karasinski, Kody Melissa Brock, Kleydson Diego Rocha, Jinyi Xia, Rodrigo Vieira Leite, Pedro Higuchi, Ana Carolina da Silva, Gabriel Maximo da Silva, Gina R. Cova and Carlos Alberto Silva

Remote Sens. 2025, 17(2), 320; https://doi.org/10.3390/rs17020320 - 17 Jan 2025

Cited by 5 | Viewed by 5851

Abstract

Southern U.S. forests are essential for carbon storage and timber production but are increasingly impacted by natural disturbances, highlighting the need to understand their dynamics and recovery. Canopy cover is a key indicator of forest health and resilience. Advances in remote sensing, such [...] Read more.

Southern U.S. forests are essential for carbon storage and timber production but are increasingly impacted by natural disturbances, highlighting the need to understand their dynamics and recovery. Canopy cover is a key indicator of forest health and resilience. Advances in remote sensing, such as NASA’s GEDI spaceborne LiDAR, enable more precise mapping of canopy cover. Although GEDI provides accurate data, its limited spatial coverage restricts large-scale assessments. To address this, we combined GEDI with Synthetic Aperture Radar (SAR), and optical imagery (Sentinel-1 GRD and Landsat–Sentinel Harmonized (HLS)) data to create a comprehensive canopy cover map for Florida. Using a random forest algorithm, our model achieved an R² of 0.69, RMSD of 0.17, and MD of 0.001, based on out-of-bag samples for internal validation. Geographic coordinates and the red spectral channel emerged as the most influential predictors. External validation with airborne laser scanning (ALS) data across three sites yielded an R² of 0.70, RMSD of 0.29, and MD of −0.22, confirming the model’s accuracy and robustness in unseen areas. Statewide analysis showed lower canopy cover in southern versus northern Florida, with wetland forests exhibiting higher cover than upland sites. This study demonstrates the potential of integrating multiple remote sensing datasets to produce accurate vegetation maps, supporting forest management and sustainability efforts in Florida. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Figure 1

27 pages, 20827 KB

Open AccessEditor’s ChoiceArticle

Three-Dimensional Reconstruction of Space Targets Utilizing Joint Optical-and-ISAR Co-Location Observation

by Wanting Zhou, Lei Liu, Rongzhen Du, Ze Wang, Ronghua Shang and Feng Zhou

Remote Sens. 2025, 17(2), 287; https://doi.org/10.3390/rs17020287 - 15 Jan 2025

Cited by 10 | Viewed by 2501

Abstract

With traditional three-dimensional (3-D) reconstruction methods for space targets, it is difficult to achieve 3-D structure and attitude reconstruction simultaneously. To tackle this problem, a 3-D reconstruction method for space targets is proposed, and the alignment and fusion of optical and ISAR images [...] Read more.

With traditional three-dimensional (3-D) reconstruction methods for space targets, it is difficult to achieve 3-D structure and attitude reconstruction simultaneously. To tackle this problem, a 3-D reconstruction method for space targets is proposed, and the alignment and fusion of optical and ISAR images are investigated. Firstly, multiple pairs of optical and ISAR images are acquired in the joint optical-and-ISAR co-location observation system (COS). Then, key points of space targets on the images are used to solve for the Doppler information and the 3-D attitude. Meanwhile, the image offsets of each pair are further aligned based on Doppler co-projection between optical and ISAR images. The 3-D rotational offset relationship and the 3-D translational offset relationship are next deduced to align the spatial offset between pairs of images based on attitude changes in neighboring frames. Finally, a voxel trimming mechanism based on growth learning (VTM-GL) is designed to obtain the reserved voxels where mask features are used. Experimental results verify the effectiveness and robustness of the OC-V3R-OI method. Full article

(This article belongs to the Special Issue Machine Vision and Advanced Image Processing in Remote Sensing (Third Edition))

► Show Figures

Graphical abstract

29 pages, 19709 KB

Open AccessEditor’s ChoiceArticle

Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning

by David Hartmann, Mathieu Gravey, Timothy David Price, Wiebe Nijland and Steven Michael de Jong

Remote Sens. 2025, 17(2), 291; https://doi.org/10.3390/rs17020291 - 15 Jan 2025

Cited by 10 | Viewed by 4948

Abstract

Nearshore bathymetric data are essential for assessing coastal hazards, studying benthic habitats and for coastal engineering. Traditional bathymetry mapping techniques of ship-sounding and airborne LiDAR are laborious, expensive and not always efficient. Multispectral and hyperspectral remote sensing, in combination with machine learning techniques, [...] Read more.

Nearshore bathymetric data are essential for assessing coastal hazards, studying benthic habitats and for coastal engineering. Traditional bathymetry mapping techniques of ship-sounding and airborne LiDAR are laborious, expensive and not always efficient. Multispectral and hyperspectral remote sensing, in combination with machine learning techniques, are gaining interest. Here, the nearshore bathymetry of southwest Puerto Rico is estimated with multispectral Sentinel-2 and hyperspectral PRISMA imagery using conventional spectral band ratio models and more advanced XGBoost models and convolutional neural networks. The U-Net, trained on 49 Sentinel-2 images, and the 2D-3D CNN, trained on PRISMA imagery, had a Mean Absolute Error (MAE) of approximately 1 m for depths up to 20 m and were superior to band ratio models by ~40%. Problems with underprediction remain for turbid waters. Sentinel-2 showed higher performance than PRISMA up to 20 m (~18% lower MAE), attributed to training with a larger number of images and employing an ensemble prediction, while PRISMA outperformed Sentinel-2 for depths between 25 m and 30 m (~19% lower MAE). Sentinel-2 imagery is recommended over PRISMA imagery for estimating shallow bathymetry given its similar performance, much higher image availability and easier handling. Future studies are recommended to train neural networks with images from various regions to increase generalization and method portability. Models are preferably trained by area-segregated splits to ensure independence between the training and testing set. Using a random train test split for bathymetry is not recommended due to spatial autocorrelation of sea depth, resulting in data leakage. This study demonstrates the high potential of machine learning models for assessing the bathymetry of optically shallow waters using optical satellite imagery. Full article

(This article belongs to the Section Environmental Remote Sensing)

► Show Figures

Graphical abstract

21 pages, 16279 KB

Open AccessEditor’s ChoiceArticle

Projected Spatiotemporal Evolution of Urban Form Using the SLEUTH Model with Urban Master Plan Scenarios

by Yuhan Liu, Caiyan Wu, Jiong Wu, Yangcen Zhang, Xing Bi, Meng Wang, Enrong Yan, Conghe Song and Junxiang Li

Remote Sens. 2025, 17(2), 270; https://doi.org/10.3390/rs17020270 - 14 Jan 2025

Cited by 7 | Viewed by 4376

Abstract

Urban growth, a pivotal characteristic of economic development, brings many environmental and ecological challenges. Modeling urban growth is essential for understanding its spatial dynamics and projecting future trends, providing insights for effective urban planning and sustainable development. This study aims to assess the [...] Read more.

Urban growth, a pivotal characteristic of economic development, brings many environmental and ecological challenges. Modeling urban growth is essential for understanding its spatial dynamics and projecting future trends, providing insights for effective urban planning and sustainable development. This study aims to assess the spatiotemporal patterns of urban growth and morphological evolution in mainland Shanghai from 2016 to 2060 using the SLEUTH model under multiple growth scenarios based on the Shanghai Urban Master Plan (2017–2035). A comprehensive set of urban growth metrics and quadrant analysis were employed to quantify the magnitude, rate, intensity, and direction of urban growth, as well as morphological evolution, over time. We found that (1) significant urban growth was observed across most scenarios, with the exception of stringent land protection. The most substantial growth occurred prior to 2045 with an obvious north–south disparity, where southern regions demonstrated more pronounced increases in urban land area and urbanization rates. (2) The spatiotemporal patterns of the rate and intensity of urban growth exhibited similar characteristics. The spatial pattern followed a “concave shape” pattern and displayed anisotropic behavior, with the high values for these indicators primarily observed before 2025. (3) The urban form followed a diffusion–coalescence process, with patch areas dominated by the infilling mode and patch numbers dominated by the edge-expansion mode. This resulted in significant alternating urban growth models in the infilling, edge-expansion, and leapfrog modes over time, influenced by varying protection intensities. These findings provide valuable insights for forward-looking urban planning, land use optimization, and the support of sustainable urban development. Full article

(This article belongs to the Special Issue Urban Planning Supported by Remote Sensing Technology II)

► Show Figures

Graphical abstract

20 pages, 11254 KB

Open AccessEditor’s ChoiceArticle

SCM-YOLO for Lightweight Small Object Detection in Remote Sensing Images

by Hao Qiang, Wei Hao, Meilin Xie, Qiang Tang, Heng Shi, Yixin Zhao and Xiaoteng Han

Remote Sens. 2025, 17(2), 249; https://doi.org/10.3390/rs17020249 - 12 Jan 2025

Cited by 35 | Viewed by 7747

Abstract

Currently, small object detection in complex remote sensing environments faces significant challenges. The detectors designed for this scenario have limitations, such as insufficient extraction of spatial local information, inflexible feature fusion, and limited global feature acquisition capability. In addition, there is a need [...] Read more.

Currently, small object detection in complex remote sensing environments faces significant challenges. The detectors designed for this scenario have limitations, such as insufficient extraction of spatial local information, inflexible feature fusion, and limited global feature acquisition capability. In addition, there is a need to balance performance and complexity when improving the model. To address these issues, this paper proposes an efficient and lightweight SCM-YOLO detector improved from YOLOv5 with spatial local information enhancement, multi-scale feature adaptive fusion, and global sensing capabilities. The SCM-YOLO detector consists of three innovative and lightweight modules: the Space Interleaving in Depth (SPID) module, the Cross Block and Channel Reweight Concat (CBCC) module, and the Mixed Local Channel Attention Global Integration (MAGI) module. These three modules effectively improve the performance of the detector from three aspects: feature extraction, feature fusion, and feature perception. The ability of SCM-YOLO to detect small objects in complex remote sensing environments has been significantly improved while maintaining its lightweight characteristics. The effectiveness and lightweight characteristics of SCM-YOLO are verified through comparison experiments with AI-TOD and SIMD public remote sensing small object detection datasets. In addition, we validate the effectiveness of the three modules, SPID, CBCC, and MAGI, through ablation experiments. The comparison experiments on the AI-TOD dataset show that the mAP50 and mAP50-95 metrics of SCM-YOLO reach 64.053% and 27.283%, respectively, which are significantly better than other models with the same parameter size. Full article

(This article belongs to the Special Issue Advanced Artificial Intelligence and Deep Learning for Remote Sensing II)

► Show Figures

Figure 1

23 pages, 7550 KB

Open AccessEditor’s ChoiceArticle

Spatiotemporal Changes in Evapotranspiration and Its Influencing Factors in the Jiziwan Region of the Yellow River from 1982 to 2018

by Wenting Liu, Rong Tang, Ge Zhang, Jiacong Xue, Baolin Xue and Yuntao Wang

Remote Sens. 2025, 17(2), 252; https://doi.org/10.3390/rs17020252 - 12 Jan 2025

Cited by 11 | Viewed by 1928

Abstract

Evapotranspiration (ET) is a critical process in the interaction between the terrestrial climate system and vegetation. In recent years, ET has undergone significant changes in the Jiziwan region of the Yellow River Basin, primarily due to the implementation of ecological restoration programs and [...] Read more.

Evapotranspiration (ET) is a critical process in the interaction between the terrestrial climate system and vegetation. In recent years, ET has undergone significant changes in the Jiziwan region of the Yellow River Basin, primarily due to the implementation of ecological restoration programs and the dual impacts of climate change. As a result, hydrological cycle processes have been profoundly affected, making it crucial to accurately capture trends in ET and its components, as well as to identify the key drivers of these changes. In this study, we first systematically analyzed the dynamic evolution of ET and its components in the Jiziwan of the Yellow River area between 1982 and 2018 from the perspective of land use change. To achieve accurate ET simulations, we introduced a multiple linear regression algorithm and quantitatively evaluated the specific contributions of five climate factors, including precipitation, temperature, wind speed, specific humidity, and radiation, as well as the normalized difference vegetation index (NDVI), a vegetation factor, to ET and its components. On this basis, we explored the combined influence mechanism of climate change and vegetation change on ET in detail. The results revealed that the structure of ET in the Jiziwan of the Yellow River area has changed significantly and that vegetation evapotranspiration has gradually replaced soil evaporation, occupies a dominant position, and has become the main component of ET in this area. Among the many factors affecting ET, the contribution of climate change is the most significant, with an average contribution rate of approximately 59%. Moreover, the influence of human activities on total ET and its components is also high. The factors that had the greatest impact on total ET, soil evaporation, and vegetation transpiration were precipitation, radiation, and the NDVI, respectively. In terms of spatial distribution, the eastern part of Jiziwan was more significantly affected by environmental changes, and the trends of the ET changes were more dramatic. This study not only enhances our scientific understanding of the changes in ET and their driving mechanisms in the Jiziwan area of the Yellow River but also provides a solid scientific foundation for the development of water resource management and ecological restoration strategies in the region. Full article

(This article belongs to the Special Issue Quantitative Remote Sensing of Vegetation and Its Applications)

► Show Figures

Figure 1

27 pages, 27746 KB

Open AccessEditor’s ChoiceArticle

Multi-Criteria Assessment of Urban Thermal Hotspots: A GIS-Based Remote Sensing Approach in a Mediterranean Climate City

by Javier Sola-Caraballo, Antonio Serrano-Jiménez, Carlos Rivera-Gomez and Carmen Galan-Marin

Remote Sens. 2025, 17(2), 231; https://doi.org/10.3390/rs17020231 - 10 Jan 2025

Cited by 16 | Viewed by 8348

Abstract

One of the most significant urban challenges focuses on addressing the effects of urban overheating as a consequence of climate change. Several methods have been developed to characterize urban heat islands (UHIs); however, the most widely used involve complex planning, huge time consumption, [...] Read more.

One of the most significant urban challenges focuses on addressing the effects of urban overheating as a consequence of climate change. Several methods have been developed to characterize urban heat islands (UHIs); however, the most widely used involve complex planning, huge time consumption, and substantial human and technical resources on field monitoring campaigns. Therefore, this study aims to provide an easily accessible and affordable remote sensing method for locating urban hotspots and addresses a multi-criteria assessment of urban heat-related parameters, allowing for a comprehensive city-wide evaluation. The novelty is based on leveraging the potential of the last Landsat 9 satellite, the application of kernel spatial interpolation, and GIS open access data, providing very high-resolution land surface temperature images over urban spaces. Within GIS workflow, the city is divided into LCZs, thermal hotspots are detected, and finally, it is analyzed to understand how urban factors, such as urban boundaries, building density, and vegetation, affect urban scale LST, all using graphical and analytical cross-assessment. The methodology has been tested in Seville, a representative warm Mediterranean city, where variations of up to 10 °C have been found between homogeneous residential areas. Thermal hotspots have been located, representing 11% of the total residential fabric, while results indicate a clear connection between the urban factors studied and overheating. The conclusions support the possibility of generating a powerful affordable tool for future research and the design of public policy renewal actions in vulnerable areas. Full article

(This article belongs to the Special Issue Multi-Platform Remote Sensing for the Modeling and Analysis of Smart Cities)

► Show Figures

Figure 1

23 pages, 8216 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Random Cross-Validation Produces Biased Assessment of Machine Learning Performance in Regional Landslide Susceptibility Prediction

by Chandan Kumar, Gabriel Walton, Paul Santi and Carlos Luza

Remote Sens. 2025, 17(2), 213; https://doi.org/10.3390/rs17020213 - 9 Jan 2025

Cited by 41 | Viewed by 7292

Abstract

Machine learning (ML) models are extensively used in spatial predictive modeling, including landslide susceptibility prediction. The performance statistics of these models are vital for assessing their reliability, which is typically obtained using the random cross-validation (R-CV) method. However, R-CV has a major drawback, [...] Read more.

Machine learning (ML) models are extensively used in spatial predictive modeling, including landslide susceptibility prediction. The performance statistics of these models are vital for assessing their reliability, which is typically obtained using the random cross-validation (R-CV) method. However, R-CV has a major drawback, i.e., it ignores the spatial autocorrelation (SAC) inherent in spatial datasets when partitioning the training and testing sets. We assessed the impact of SAC at three crucial phases of ML modeling: hyperparameter tuning, performance evaluation, and learning curve analysis. As an alternative to R-CV, we used spatial cross-validation (S-CV). This method considers SAC when partitioning the training and testing subsets. This experiment was conducted on regional landslide susceptibility prediction using different ML models: logistic regression (LR), k-nearest neighbor (KNN), linear discriminant analysis (LDA), artificial neural networks (ANN), support vector machine (SVM), random forest (RF), and C5.0. The experimental results showed that R-CV often produces optimistic performance estimates, e.g., 6–18% higher than those obtained using the S-CV. R-CV also occasionally fails to reveal the true importance of the hyperparameters of models such as SVM and ANN. Additionally, R-CV falsely portrays a considerable improvement in model performance as the number of variables increases. However, this was not the case when the models were evaluated using S-CV. The impact of SAC was more noticeable in complex models such as SVM, RF, and C5.0 (except for ANN) than in simple models such as LDA and LR (except for KNN). Overall, we recommend S-CV over R-CV for a reliable assessment of ML model performance in large-scale LSM. Full article

(This article belongs to the Special Issue Assessing Natural Hazards through Advanced Machine Learning Methods and Remote Sensing Technology: 3rd Edition)

► Show Figures

Graphical abstract

17 pages, 7188 KB

Open AccessEditor’s ChoiceArticle

Understanding the Influence of Image Enhancement on Underwater Object Detection: A Quantitative and Qualitative Study

by Ashraf Saleem, Ali Awad, Sidike Paheding, Evan Lucas, Timothy C. Havens and Peter C. Esselman

Remote Sens. 2025, 17(2), 185; https://doi.org/10.3390/rs17020185 - 7 Jan 2025

Cited by 18 | Viewed by 5496

Abstract

Underwater image enhancement is often perceived as a disadvantageous process to object detection. We propose a novel analysis of the interactions between enhancement and detection, elaborating on the potential of enhancement to improve detection. In particular, we evaluate object detection performance for each [...] Read more.

Underwater image enhancement is often perceived as a disadvantageous process to object detection. We propose a novel analysis of the interactions between enhancement and detection, elaborating on the potential of enhancement to improve detection. In particular, we evaluate object detection performance for each individual image rather than across the entire set to allow a direct performance comparison of each image before and after enhancement. This approach enables the generation of unique queries to identify the outperforming and underperforming enhanced images compared to the original images. To accomplish this, we first produce enhanced image sets of the original images using recent image enhancement models. Each enhanced set is then divided into two groups: (1) images that outperform or match the performance of the original images and (2) images that underperform. Subsequently, we create mixed original-enhanced sets by replacing underperforming enhanced images with their corresponding original images. Next, we conduct a detailed analysis by evaluating all generated groups for quality and detection performance attributes. Finally, we perform an overlap analysis between the generated enhanced sets to identify cases where the enhanced images of different enhancement algorithms unanimously outperform, equally perform, or underperform the original images. Our analysis reveals that, when evaluated individually, most enhanced images achieve equal or superior performance compared to their original counterparts. The proposed method uncovers variations in detection performance that are not apparent in a whole set as opposed to a per-image evaluation because the latter reveals that only a small percentage of enhanced images cause an overall negative impact on detection. We also find that over-enhancement may lead to deteriorated object detection performance. Lastly, we note that enhanced images reveal hidden objects that were not annotated due to the low visibility of the original images. Full article

(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Enhancement)

► Show Figures

Figure 1

23 pages, 26242 KB

Open AccessEditor’s ChoiceArticle

The Application of Fast Fourier Transform Filtering to High Spatial Resolution Digital Terrain Models Derived from LiDAR Sensors for the Objective Mapping of Surface Features and Digital Terrain Model Evaluations

by Alberto González-Díez, Ignacio Díaz-Martínez, Pablo Cruz-Hernández, Antonio Barreda-Argüeso and Matthew Doughty

Remote Sens. 2025, 17(1), 150; https://doi.org/10.3390/rs17010150 - 4 Jan 2025

Cited by 2 | Viewed by 3919

Abstract

In this paper, the application is investigated of fast Fourier transform filtering (FFT-FR) to high spatial resolution digital terrain models (HR-DTM) derived from LiDAR sensors, assessing its efficacy in identifying genuine relief elements, including both natural geological features and anthropogenic landforms. The suitability [...] Read more.

In this paper, the application is investigated of fast Fourier transform filtering (FFT-FR) to high spatial resolution digital terrain models (HR-DTM) derived from LiDAR sensors, assessing its efficacy in identifying genuine relief elements, including both natural geological features and anthropogenic landforms. The suitability of the derived filtered geomorphic references (FGRs) is evaluated through spatial correlation with ground truths (GTs) extracted from the topographical and geological geodatabases of Santander Bay, Northern Spain. In this study, it is revealed that existing artefacts, derived from vegetation or human infrastructures, pose challenges in the units’ construction, and large physiographic units are better represented using low-pass filters, whereas detailed units are more accurately depicted with high-pass filters. The results indicate a propensity of high-frequency filters to detect anthropogenic elements within the DTM. The quality of GTs used for validation proves more critical than the geodatabase scale. Additionally, in this study, it is demonstrated that the footprint of buildings remains uneliminated, indicating that the model is a poorly refined digital surface model (DSM) rather than a true digital terrain model (DTM). Experiments validate the DTM’s capability to highlight contacts and constructions, with water detection showing high precision (≥60%) and varying precision for buildings. Large units are better captured with low filters, whilst high filters effectively detect anthropogenic elements and more detailed units. This facilitates the design of validation and correction procedures for DEMs derived from LiDAR point clouds, enhancing the potential for more accurate and objective Earth surface representation. Full article

(This article belongs to the Special Issue Objective Mapping of Terrestrial and Planetary Surface Features: Remote Sensing in Geosciences)

► Show Figures

Figure 1

25 pages, 13675 KB

Open AccessEditor’s ChoiceArticle

KANDiff: Kolmogorov–Arnold Network and Diffusion Model-Based Network for Hyperspectral and Multispectral Image Fusion

by Wei Li, Lu Li, Man Peng and Ran Tao

Remote Sens. 2025, 17(1), 145; https://doi.org/10.3390/rs17010145 - 3 Jan 2025

Cited by 13 | Viewed by 4421

Abstract

In recent years, the fusion of hyperspectral and multispectral images in remote sensing image processing still faces challenges, primarily due to their complexity and multimodal characteristics. Diffusion models, known for their stable training process and exceptional image generation capabilities, have shown good application [...] Read more.

In recent years, the fusion of hyperspectral and multispectral images in remote sensing image processing still faces challenges, primarily due to their complexity and multimodal characteristics. Diffusion models, known for their stable training process and exceptional image generation capabilities, have shown good application potential in this field. However, when dealing with multimodal data, it may prove challenging for the models to fully capture the intricate relationships between the modalities, which may result in incomplete information integration and a small amount of remaining noise in the generated images. To address these problems, we propose a new model, KanDiff, for hyperspectral and multispectral image fusion. To address the differences in modal information between multispectral and hyperspectral images, KANDiff incorporates Kolmogorov–Arnold Networks (KAN) to guide the inputs. It helps the model understand the complex relationships between the modalities by replacing the fixed activation function in the traditional MLP with a learnable activation function. Furthermore, the image generated by the diffusion model may exhibit a small amount of the remaining noise. Convolutional Neural Networks (CNNs) effectively extract local features through their convolutional layers and achieve noise suppression via layer-by-layer feature representation. Therefore, the MergeCNN module is further introduced to enhance the fusion effect, resulting in smoother and more accurate outcomes. Experimental results on the public CAVE and Harvard datasets indicate that KanDiff has achieved improvements over current high-performance methods across several metrics, particularly showing significant enhancements in the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM), thus demonstrating superior performance. Additionally, we have created an image fusion dataset of the lunar surface, and KANDiff exhibits robust performance on this dataset as well. This work introduces an effective solution for addressing the challenges posed by missing high-resolution hyperspectral images (HRHS) data, which is essential for tasks including landing site selection and resource exploration within the realm of deep space exploration. Full article

(This article belongs to the Section Remote Sensing Image Processing)

► Show Figures

Figure 1

24 pages, 11292 KB

Open AccessEditor’s ChoiceArticle

Inversion of Water Quality Parameters from UAV Hyperspectral Data Based on Intelligent Algorithm Optimized Backpropagation Neural Networks of a Small Rural River

by Manqi Wang, Caili Zhou, Jiaqi Shi, Fei Lin, Yucheng Li, Yimin Hu and Xuesheng Zhang

Remote Sens. 2025, 17(1), 119; https://doi.org/10.3390/rs17010119 - 2 Jan 2025

Cited by 19 | Viewed by 3784

Abstract

The continuous and effective monitoring of the water quality of small rural rivers is crucial for rural sustainable development. In this work, machine learning models were established to predict the water quality of a typical small rural river based on a small quantity [...] Read more.

The continuous and effective monitoring of the water quality of small rural rivers is crucial for rural sustainable development. In this work, machine learning models were established to predict the water quality of a typical small rural river based on a small quantity of measured water quality data and UAV hyperspectral images. Firstly, the spectral data were preprocessed using fractional order derivation (FOD), standard normal variate (SNV), and normalization (Norm) to enhance the spectral response characteristics of the water quality parameters. Second, a method combining the Pearson’s correlation coefficient and the variance inflation factor (PCC–VIF) was utilized to decrease the dimensionality of features and improve the quality of the input data. Again, based on the screened features, a back-propagation neural network (BPNN) model optimized using a mixture of the genetic algorithm (GA) and the particle swarm optimization (PSO) algorithm was established as a means of estimating water quality parameter concentrations. To intuitively evaluate the performance of the hybrid optimization algorithm, its prediction accuracy is compared with that of conventional machine learning algorithms (Random Forest, CatBoost, XGBoost, BPNN, GA–BPNN and PSO–BPNN). The results show that the GA–PSO–BPNN model for turbidity (TUB), ammonia nitrogen (NH₃-N), total nitrogen (TN), and total phosphorus (TP) prediction exhibited optimal accuracy with coefficients of determination (R²) of 0.770, 0.804, 0.754, and 0.808, respectively. Meanwhile, the model also demonstrated good robustness and generalization ability for data from different periods. In addition, we used this method to visualize the water quality parameters in the study area. This work provides a new approach to the refined monitoring of water quality in small rural rivers. Full article

(This article belongs to the Special Issue Impacts of Climate Change on Water Cycle and Terrestrial Ecosystems by Remote Sensing)

► Show Figures

Figure 1

23 pages, 14567 KB

Open AccessEditor’s ChoiceArticle

CloudTran++: Improved Cloud Removal from Multi-Temporal Satellite Images Using Axial Transformer Networks

by Dionysis Christopoulos, Valsamis Ntouskos and Konstantinos Karantzalos

Remote Sens. 2025, 17(1), 86; https://doi.org/10.3390/rs17010086 - 29 Dec 2024

Cited by 9 | Viewed by 4057

Abstract

We present a method for cloud removal from satellite images using axial transformer networks. The method considers a set of multi-temporal images in a given region of interest, together with the corresponding cloud masks, and produces a cloud-free image for a specific day [...] Read more.

We present a method for cloud removal from satellite images using axial transformer networks. The method considers a set of multi-temporal images in a given region of interest, together with the corresponding cloud masks, and produces a cloud-free image for a specific day of the year. We propose the combination of an encoder-decoder model employing axial attention layers for the estimation of the low-resolution cloud-free image, together with a fully parallel upsampler that reconstructs the image at full resolution. The method is compared with various baselines and state-of-the-art methods on Sentinel-2 datasets of different coverage, showing significant improvements across multiple standard metrics used for image quality assessment. Full article

(This article belongs to the Section Remote Sensing Image Processing)

► Show Figures

Graphical abstract

18 pages, 39500 KB

Open AccessEditor’s ChoiceArticle

Pre-, Co-, and Post-Failure Deformation Analysis of the Catastrophic Xinjing Open-Pit Coal Mine Landslide, China, from Optical and Radar Remote Sensing Observations

by Fengnian Chang, Houyu Li, Shaochun Dong and Hongwei Yin

Remote Sens. 2025, 17(1), 19; https://doi.org/10.3390/rs17010019 - 25 Dec 2024

Cited by 14 | Viewed by 2892

Abstract

Landslide risks in open-pit mine areas are heightened by artificial slope modifications necessary for mining operations, endangering human life and property. On 22 February 2023, a catastrophic landslide occurred at the Xinjing Open-Pit Coal Mine in Inner Mongolia, China, resulting in 53 fatalities [...] Read more.

Landslide risks in open-pit mine areas are heightened by artificial slope modifications necessary for mining operations, endangering human life and property. On 22 February 2023, a catastrophic landslide occurred at the Xinjing Open-Pit Coal Mine in Inner Mongolia, China, resulting in 53 fatalities and economic losses totaling 28.7 million USD. Investigating the pre-, co-, and post-failure deformation processes and exploring the potential driving mechanisms are crucial to preventing similar tragedies. In this study, we used multi-source optical and radar images alongside satellite geodetic methods to analyze the event. The results revealed pre-failure acceleration at the slope toe, large-scale southward displacement during collapse, and ongoing deformation across the mine area due to mining operations and waste accumulation. The collapse was primarily triggered by an excessively steep, non-compliant artificial slope design and continuous excavation at the slope’s base. Furthermore, our experiments indicated that the commonly used Sentinel-1 Interferometric Synthetic Aperture Radar (InSAR) significantly underestimated landslide deformation due to the maximum detectable deformation gradient (MDDG) limitation. In contrast, the high-spatial-resolution Fucheng-1 provided more accurate monitoring results with a higher MDDG. This underscores the importance of carefully assessing the MDDG when employing InSAR techniques to monitor rapid deformation in mining areas. Full article

(This article belongs to the Special Issue Synthetic Aperture Radar Interferometry Symposium 2024)

► Show Figures

Figure 1

23 pages, 10008 KB

Open AccessEditor’s ChoiceReview

Multi-Global Navigation Satellite System for Earth Observation: Recent Developments and New Progress

by Shuanggen Jin, Xuyang Meng, Gino Dardanelli and Yunlong Zhu

Remote Sens. 2024, 16(24), 4800; https://doi.org/10.3390/rs16244800 - 23 Dec 2024

Cited by 19 | Viewed by 5108

Abstract

The Global Navigation Satellite System (GNSS) has made important progress in Earth observation and applications. With the successful design of the BeiDou Navigation Satellite System (BDS), four global navigation satellite systems are available worldwide, together with Galileo, GLONASS, and GPS. These systems have [...] Read more.

The Global Navigation Satellite System (GNSS) has made important progress in Earth observation and applications. With the successful design of the BeiDou Navigation Satellite System (BDS), four global navigation satellite systems are available worldwide, together with Galileo, GLONASS, and GPS. These systems have been widely employed in positioning, navigation, and timing (PNT). Furthermore, GNSS refraction, reflection, and scattering signals can remotely sense the Earth’s surface and atmosphere with powerful implications for environmental remote sensing. In this paper, the recent developments and new application progress of multi-GNSS in Earth observation are presented and reviewed, including the methods of BDS/GNSS for Earth observations, GNSS navigation and positioning performance (e.g., GNSS-PPP and GNSS-NRTK), GNSS ionospheric modelling and space weather monitoring, GNSS meteorology, and GNSS-reflectometry and its applications. For instance, the static Precise Point Positioning (PPP) precision of most MGEX stations was improved by 35.1%, 18.7%, and 8.7% in the east, north, and upward directions, respectively, with PPP ambiguity resolution (AR) based on factor graph optimization. A two-layer ionospheric model was constructed using IGS station data through three-dimensional ionospheric model constraints and TEC accuracy was increased by about 20–27% with the GIM model. Ten-minute water level change with centimeter-level accuracy was estimated with ground-based multiple GNSS-R data based on a weighted iterative least-squares method. Furthermore, a cyclone and its positions were detected by utilizing the GNSS-reflectometry from the space-borne Cyclone GNSS (CYGNSS) mission. Over the years, GNSS has become a dominant technology among Earth observation with powerful applications, not only for conventional positioning, navigation and timing techniques, but also for integrated remote sensing solutions, such as monitoring typhoons, river water level changes, geological geohazard warnings, low-altitude UAV navigation, etc., due to its high performance, low cost, all time and all weather. Full article

(This article belongs to the Special Issue State of the Art of GNSS and SAR/InSAR Techniques for Geomatic Applications)

► Show Figures

Graphical abstract

29 pages, 5124 KB

Open AccessEditor’s ChoiceReview

Combination of Remote Sensing and Artificial Intelligence in Fruit Growing: Progress, Challenges, and Potential Applications

by Danielle Elis Garcia Furuya, Édson Luis Bolfe, Taya Cristo Parreiras, Jayme Garcia Arnal Barbedo, Thiago Teixeira Santos and Luciano Gebler

Remote Sens. 2024, 16(24), 4805; https://doi.org/10.3390/rs16244805 - 23 Dec 2024

Cited by 10 | Viewed by 6707

Abstract

Fruit growing is important in the global agricultural economy, contributing significantly to food security, job creation, and rural development. With the advancement of technologies, mapping fruits using remote sensing and machine learning (ML) and deep learning (DL) techniques has become an essential tool [...] Read more.

Fruit growing is important in the global agricultural economy, contributing significantly to food security, job creation, and rural development. With the advancement of technologies, mapping fruits using remote sensing and machine learning (ML) and deep learning (DL) techniques has become an essential tool to optimize production, monitor crop health, and predict harvests with greater accuracy. This study was developed in four main stages. In the first stage, a comprehensive review of the existing literature was made from July 2018 (first article found) to June 2024, totaling 117 articles. In the second stage, a general analysis of the data obtained was made, such as the identification of the most studied fruits with the techniques of interest. In the third stage, a more in-depth analysis was made focusing on apples and grapes, with 27 and 30 articles, respectively. The analysis included the use of remote sensing (orbital and proximal) imagery and ML/DL algorithms to map crop areas, detect diseases, and monitor crop development, among other analyses. The fourth stage shows the data’s potential application in a Southern Brazilian region, known for apple and grape production. This study demonstrates how the integration of modern technologies can transform fruit farming, promoting more sustainable and efficient agriculture through remote sensing and artificial intelligence technologies. Full article

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)

► Show Figures

Figure 1

16 pages, 9121 KB

Open AccessEditor’s ChoiceTechnical Note

A Benchmark Dataset for Aircraft Detection in Optical Remote Sensing Imagery

by Jianming Hu, Xiyang Zhi, Bingxian Zhang, Tianjun Shi, Qi Cui and Xiaogang Sun

Remote Sens. 2024, 16(24), 4699; https://doi.org/10.3390/rs16244699 - 17 Dec 2024

Cited by 4 | Viewed by 5430

Abstract

The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important factor restricting the effectiveness and reliability of aircraft detection algorithms. Although a large amount of research [...] Read more.

The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important factor restricting the effectiveness and reliability of aircraft detection algorithms. Although a large amount of research has been devoted to breaking through few-sample-driven aircraft detection technology, most algorithms still struggle to effectively solve the problems of missed target detection and false alarms caused by numerous environmental interferences in bird-eye optical remote sensing scenes. To further aircraft detection research, we have established a new dataset, Aircraft Detection in Complex Optical Scene (ADCOS), sourced from various platforms including Google Earth, Microsoft Map, Worldview-3, Pleiades, Ikonos, Orbview-3, and Jilin-1 satellites. It integrates 3903 meticulously chosen images of over 400 famous airports worldwide, containing 33,831 annotated instances employing the oriented bounding box (OBB) format. Notably, this dataset encompasses a wide range of various targets characteristics including multi-scale, multi-direction, multi-type, multi-state, and dense arrangement, along with complex relationships between targets and backgrounds like cluttered backgrounds, low contrast, shadows, and occlusion interference conditions. Furthermore, we evaluated nine representative detection algorithms on the ADCOS dataset, establishing a performance benchmark for subsequent algorithm optimization. The latest dataset will soon be available on the Github website. Full article

(This article belongs to the Section Earth Observation Data)

► Show Figures

Figure 1

18 pages, 5411 KB

Open AccessEditor’s ChoiceArticle

Leveraging Neural Radiance Fields for Large-Scale 3D Reconstruction from Aerial Imagery

by Max Hermann, Hyovin Kwak, Boitumelo Ruf and Martin Weinmann

Remote Sens. 2024, 16(24), 4655; https://doi.org/10.3390/rs16244655 - 12 Dec 2024

Cited by 6 | Viewed by 6784

Abstract

Since conventional photogrammetric approaches struggle with with low-texture, reflective, and transparent regions, this study explores the application of Neural Radiance Fields (NeRFs) for large-scale 3D reconstruction of outdoor scenes, since NeRF-based methods have recently shown very impressive results in these areas. We evaluate [...] Read more.

Since conventional photogrammetric approaches struggle with with low-texture, reflective, and transparent regions, this study explores the application of Neural Radiance Fields (NeRFs) for large-scale 3D reconstruction of outdoor scenes, since NeRF-based methods have recently shown very impressive results in these areas. We evaluate three approaches: Mega-NeRF, Block-NeRF, and Direct Voxel Grid Optimization, focusing on their accuracy and completeness compared to ground truth point clouds. In addition, we analyze the effects of using multiple sub-modules, estimating the visibility by an additional neural network and varying the density threshold for the extraction of the point cloud. For performance evaluation, we use benchmark datasets that correspond to the setting off standard flight campaigns and therefore typically have nadir camera perspective and relatively little image overlap, which can be challenging for NeRF-based approaches that are typically trained with significantly more images and varying camera angles. We show that despite lower quality compared to classic photogrammetric approaches, NeRF-based reconstructions provide visually convincing results in challenging areas. Furthermore, our study shows that in particular increasing the number of sub-modules and predicting the visibility using an additional neural network improves the quality of the resulting reconstructions significantly. Full article

(This article belongs to the Special Issue Deep Learning Applications of 3D Reconstruction and Visualization from Remote Sensing Imagery)

► Show Figures

Figure 1

20 pages, 4062 KB

Open AccessEditor’s ChoiceArticle

A CNN-Based Framework for Automatic Extraction of High-Resolution River Bankfull Width

by Wenqi Li, Chendi Zhang, David Puhl, Xiao Pan, Marwan A. Hassan, Stephen Bird, Kejun Yang and Yang Zhao

Remote Sens. 2024, 16(23), 4614; https://doi.org/10.3390/rs16234614 - 9 Dec 2024

Cited by 6 | Viewed by 2920

Abstract

River width is a crucial parameter that correlates and reflects the hydrological, geomorphological, and ecological characteristics of the channel. However, the width data with high spatial resolution is limited owing to the difficulties in extracting channel width under complex and variable riverine surroundings. [...] Read more.

River width is a crucial parameter that correlates and reflects the hydrological, geomorphological, and ecological characteristics of the channel. However, the width data with high spatial resolution is limited owing to the difficulties in extracting channel width under complex and variable riverine surroundings. To address this issue, we aimed to develop an automatic framework specifically for delineating river channels and measuring the bankfull widths at small spatial intervals along the channel. The DeepLabV3+ Convolutional Neural Network (CNN) model was employed to accurately delineate channel boundaries and a Voronoi Diagram approach was complemented as the river width algorithm (RWA) to calculate river bankfull widths. The CNN model was trained by images across four river types and performed well with all the evaluating metrics (mIoU, Accuracy, F1-score, and Recall) higher than 0.97, referring to the accuracy over 97% in prediction. The RWA outperformed other existing river width calculation methods by showing lower errors. The application of the framework in the Lillooet River, Canada, presented the capacity of this methodology to obtain detailed distributions of hydraulic and hydrological parameters, including flow resistance, flow energy, and sediment transport capacity, based on high-resolution channel widths. Our work highlights the significant potential of the newly developed framework in acquiring high-resolution channel width information and characterizing fluvial dynamics based on these widths along river channels, which contributes to facilitating cost-effective integrated river management. Full article

(This article belongs to the Special Issue Remote Sensing in Geomatics (Second Edition))

► Show Figures

Figure 1

20 pages, 3750 KB

Open AccessEditor’s ChoiceArticle

An Automatic Modulation Recognition Algorithm Based on Time–Frequency Features and Deep Learning with Fading Channels

by Xiaoya Zuo, Yuan Yang, Rugui Yao, Ye Fan and Lu Li

Remote Sens. 2024, 16(23), 4550; https://doi.org/10.3390/rs16234550 - 4 Dec 2024

Cited by 15 | Viewed by 4844

Abstract

Automatic modulation recognition (AMR) stands as a crucial core technology within the realm of signal processing and perception, playing a significant part in harsh electromagnetic environments. The time–frequency image (TFI) of communication signals can manifest modulation characteristics and serve as a foundation for [...] Read more.

Automatic modulation recognition (AMR) stands as a crucial core technology within the realm of signal processing and perception, playing a significant part in harsh electromagnetic environments. The time–frequency image (TFI) of communication signals can manifest modulation characteristics and serve as a foundation for signal modulation recognition and classification. However, under the influence of the electromagnetic environment, communication signals are exposed to varying degrees of interference, which poses a challenge to the recognition of modulation types. Taking into account the effects of interference and channel fading, this paper introduces a communication signal modulation recognition algorithm based on deep learning (DL) and time–frequency analysis. This approach employs short-time Fourier transform (STFT) to generate time–frequency diagrams from time-domain signals. Subsequently, it binarizes the image and feeds it as input data to the neural network. Our research presents a composite deep convolutional neural network (CNN) architecture known as the composite dense-residual neural network (CDRNN). This architecture focuses on enhancing the feature extraction and identification, aiming to achieve accurate recognition of modulation types in harsh electromagnetic environments. Finally, simulation results validate that the proposed deep learning algorithm holds remarkable advantages in boosting the accuracy of modulation type recognition with better adaptability. The algorithm shows better performance even in harsh electromagnetic environments. When the signal-to-noise ratio (SNR) is 18 dB, the recognition accuracy can reach 92.1%. Full article

(This article belongs to the Special Issue Signal Processing Theory and Methods in Remote Sensing (Second Edition))

► Show Figures

Figure 1

51 pages, 19385 KB

Open AccessEditor’s ChoiceReview

Remote Sensing in Bridge Digitalization: A Review

by Joan R. Casas, Rolando Chacón, Necati Catbas, Belén Riveiro and Daniel Tonelli

Remote Sens. 2024, 16(23), 4438; https://doi.org/10.3390/rs16234438 - 27 Nov 2024

Cited by 13 | Viewed by 6118

Abstract

A review of the application of remote sensing technologies in the SHM and management of existing bridges is presented, showing their capabilities and advantages, as well as the main drawbacks when specifically applied to bridge assets. The main sensing technologies used as corresponding [...] Read more.

A review of the application of remote sensing technologies in the SHM and management of existing bridges is presented, showing their capabilities and advantages, as well as the main drawbacks when specifically applied to bridge assets. The main sensing technologies used as corresponding platforms are discussed. This is complemented by the presentation of five case studies emphasizing the wide field of application in several bridge typologies and the justification for the selection of the optimal techniques depending on the objectives of the monitoring and assessment of a particular bridge. The review shows the potentiality of remote sensing technologies in the decision-making process regarding optimal interventions in bridge management. The data gathered by them are the mandatory precursors for determining the relevant performance indicators needed for the quality control of these important infrastructure assets. Full article

(This article belongs to the Special Issue Structural Health Monitoring and Damage Assessment by Advanced Remote Sensing Techniques and Methods)

► Show Figures

Figure 1

17 pages, 12379 KB

Open AccessEditor’s ChoiceArticle

Artificial-Intelligence-Based Classification to Unveil Geodynamic Processes in the Eastern Alps

by Christian Bignami, Alessandro Pignatelli, Giulia Romoli and Carlo Doglioni

Remote Sens. 2024, 16(23), 4364; https://doi.org/10.3390/rs16234364 - 22 Nov 2024

Cited by 1 | Viewed by 1920

Abstract

InSAR has emerged as a leading technique for studying and monitoring ground movements over large areas and across various geodynamic environments. Recent advancements in SAR sensor technology have enabled the acquisition of dense spatial datasets, providing substantial information at regional and national scales. [...] Read more.

InSAR has emerged as a leading technique for studying and monitoring ground movements over large areas and across various geodynamic environments. Recent advancements in SAR sensor technology have enabled the acquisition of dense spatial datasets, providing substantial information at regional and national scales. Despite these improvements, classifying and interpreting such vast datasets remains a significant challenge. InSAR analysts and geologists frequently have to manually analyze the time series from Persistent Scatterer Interferometry (PSI) to model the complexity of geological and tectonic phenomena. This process is time-consuming and impractical for large-scale monitoring. Utilizing Artificial Intelligence (AI) to classify and detect deformation processes presents a promising solution. In this study, vertical ground deformation time series from northeastern Italy were obtained from the European Ground Motion Service and classified by experts into different deformation categories. Convolutional and pre-trained neural networks were then trained and tested using both numerical time-series data and trend images. The application of the best performing trained network to test data showed an accuracy of

83 %

. Such a result demonstrates that neural networks can successfully identify areas experiencing distinct geodynamic processes, emphasizing the potential of AI to improve PSI data interpretation. Full article

(This article belongs to the Special Issue Signal Processing and Machine Learning for Space Geodesy Applications)

► Show Figures

Figure 1

22 pages, 2412 KB

Open AccessEditor’s ChoiceReview

Remote Sensing Technologies Using UAVs for Pest and Disease Monitoring: A Review Centered on Date Palm Trees

by Bashar Alsadik, Florian J. Ellsäßer, Muheeb Awawdeh, Abdulla Al-Rawabdeh, Lubna Almahasneh, Sander Oude Elberink, Doaa Abuhamoor and Yolla Al Asmar

Remote Sens. 2024, 16(23), 4371; https://doi.org/10.3390/rs16234371 - 22 Nov 2024

Cited by 34 | Viewed by 10967

Abstract

This review is aimed at exploring the use of remote sensing technology with a focus on Unmanned Aerial Vehicles (UAVs) in monitoring and management of palm pests and diseases with a special focus on date palms. It highlights the most common sensor types, [...] Read more.

This review is aimed at exploring the use of remote sensing technology with a focus on Unmanned Aerial Vehicles (UAVs) in monitoring and management of palm pests and diseases with a special focus on date palms. It highlights the most common sensor types, ranging from passive sensors such as RGB, multispectral, hyperspectral, and thermal as well as active sensors such as light detection and ranging (LiDAR), expounding on their unique functions and gains as far as the detection of pest infestation and disease symptoms is concerned. Indices derived from UAV multispectral and hyperspectral sensors are used to assess their usefulness in vegetation health monitoring and plant physiological changes. Other UAVs are equipped with thermal sensors to identify water stress and temperature anomalies associated with the presence of pests and diseases. Furthermore, the review discusses how LiDAR technology can be used to capture detailed 3D canopy structures as well as volume changes that may occur during the progressing stages of a date palm infection. Besides, the paper examines how machine learning algorithms have been incorporated into remote sensing technologies to ensure high accuracy levels in detecting diseases or pests. This paper aims to present a comprehensive outline for future research focusing on modern methodologies, technological improvements, and direction for the efficient application of UAV-based remote sensing in managing palm tree pests and diseases. Full article

(This article belongs to the Special Issue State-of-the-Art on Satellite and UAV Remote Sensing in Geoscience Research)

► Show Figures

Figure 1

24 pages, 14942 KB

Open AccessEditor’s ChoiceArticle

The Ground-Penetrating Radar Image Matching Method Based on Central Dense Structure Context Features

by Jie Xu, Qifeng Lai, Dongyan Wei, Xinchun Ji, Ge Shen and Hong Yuan

Remote Sens. 2024, 16(22), 4291; https://doi.org/10.3390/rs16224291 - 18 Nov 2024

Cited by 6 | Viewed by 3529

Abstract

Subsurface structural distribution can be detected using Ground-Penetrating Radar (GPR). The distribution can be considered as road fingerprints for vehicle positioning. Similar to the principle of visual image matching for localization, the position coordinates of the vehicle can be calculated by matching real-time [...] Read more.

Subsurface structural distribution can be detected using Ground-Penetrating Radar (GPR). The distribution can be considered as road fingerprints for vehicle positioning. Similar to the principle of visual image matching for localization, the position coordinates of the vehicle can be calculated by matching real-time GPR images with pre-constructed reference GPR images. However, GPR images, due to their low resolution, cannot extract well-defined geometric features such as corners and lines. Thus, traditional visual image processing algorithms perform inadequately when applied to GPR image matching. To address this issue, this paper innovatively proposes a GPR image matching and localization method based on a novel feature descriptor, termed as central dense structure context (CDSC) features. The algorithm utilizes the strip-like elements in GPR images to improve the accuracy of GPR image matching. First, a CDSC feature descriptor is designed. By applying threshold segmentation and extremum point extraction to the GPR image, stratified strip-like elements and pseudo-corner points are obtained. The pseudo-corner points are treated as the centers, and the surrounding strip-like elements are described in context to form the GPR feature descriptors. Then, based on the feature description method, feature descriptors for both the real-time image and the reference image are calculated separately. By searching for the nearest matching point pairs and removing erroneous pairs, GPR image matching and localization are achieved. The proposed algorithm was evaluated on datasets collected from urban roads and railway tracks, achieving localization errors of 0.06 m (RMSE) and 1.22 m (RMSE), respectively. Compared to the traditional Speeded Up Robust Features (SURF) visual image matching algorithm, localization errors were reduced by 86.6% and 95.7% in urban road and railway track scenarios, respectively. Full article

(This article belongs to the Special Issue Advanced Ground-Penetrating Radar (GPR) Technologies and Applications)

► Show Figures

Graphical abstract

22 pages, 8045 KB

Open AccessEditor’s ChoiceArticle

A GIS Plugin for the Assessment of Deformations in Existing Bridge Portfolios via MTInSAR Data

by Mirko Calò, Sergio Ruggieri, Andrea Nettis and Giuseppina Uva

Remote Sens. 2024, 16(22), 4293; https://doi.org/10.3390/rs16224293 - 18 Nov 2024

Cited by 17 | Viewed by 1971

Abstract

The paper presents a GIS plugin, named Bridge Assessment System via MTInSAR (BAS-MTInSAR), aimed at assessing deformations in existing simply supported concrete girder bridges through Multi-Temporal Interferometry Synthetic Aperture Radar (MTInSAR). Existing bridges require continuous maintenance to ensure functionality toward external effects undermining [...] Read more.

The paper presents a GIS plugin, named Bridge Assessment System via MTInSAR (BAS-MTInSAR), aimed at assessing deformations in existing simply supported concrete girder bridges through Multi-Temporal Interferometry Synthetic Aperture Radar (MTInSAR). Existing bridges require continuous maintenance to ensure functionality toward external effects undermining the safety of these structures, such as aging, material degradation, and environmental factors. Although effective and standardized methodologies exist (e.g., structural monitoring, periodic onsite inspections), new emerging technologies could be employed to provide time- and cost-effective information on the current state of structures and to drive prompt interventions to mitigate risk. One example is represented by MTInSAR data, which can provide near-continuous information about structural displacements over time. To easily manage these data, the paper presents BAS-MTInSAR. The tool allows users to insert information of the focused bridge (displacement time series, structural information, temperature data) and, through a user-friendly GUI, observe the occurrence of abnormal deformations. In addition, the tool implements a procedure of multisource data management and defines proper thresholds to assess bridge behavior against current code prescriptions. BAS-MTInSAR is fully described throughout the text and was tested on a real case study, showing the main potentialities of the tool in managing bridge portfolios. Full article

(This article belongs to the Special Issue Structural Health Monitoring and Damage Assessment by Advanced Remote Sensing Techniques and Methods)

► Show Figures

Figure 1

19 pages, 19888 KB

Open AccessEditor’s ChoiceArticle

Improvement of Coal Mining-Induced Subsidence-Affected (MISA) Zone Irregular Boundary Delineation by MT-InSAR Techniques, UAV Photogrammetry, and Field Investigation

by Linan Liu, Nengxiong Xu, Wendy Zhou, Yan Qin and Shilong Luan

Remote Sens. 2024, 16(22), 4221; https://doi.org/10.3390/rs16224221 - 12 Nov 2024

Cited by 7 | Viewed by 3308

Abstract

Coal mining-induced ground subsidence is a severe hazard that can damage property, infrastructure, and the environment in the vicinity when the deformation is not negligible. The boundary of a mining-induced subsidence-affected zone refers to the area beyond which the ground subsidence is less [...] Read more.

Coal mining-induced ground subsidence is a severe hazard that can damage property, infrastructure, and the environment in the vicinity when the deformation is not negligible. The boundary of a mining-induced subsidence-affected zone refers to the area beyond which the ground subsidence is less concerned. Accurately measuring mining-induced ground deformation is essential for delineating the irregular boundary of the impacted area. This study employs multitemporal interferometric synthetic aperture radar (MT-InSAR) techniques, including differential InSAR (DInSAR), InSAR stacking, and interferometric point target analysis (IPTA), to analyze coal mine subsidence and delineate the boundaries of the mining-impacted zones. DInSAR accurately reconstructs, locates, and detects the trend in mining-induced subsidence and correlates well with documented mining operations. The InSAR stacking method maps the spatial variation of the ground’s average line-of-sight (LOS) velocity over the mining area, delineating the boundary of the impacted zone. IPTA analysis combining multilook and single-pixel phases achieves millimeter-level surface measurement above tunnel alignments and measures unevenly distributed deformation fields. This study considers an average of 4 cm per year of surface deformation in the LOS direction as the subsidence threshold value for delineating the boundary of the mining-induced subsidence-affected (MISA) zone during the active coal mining stage. Interestingly, there are twin transportation tunnels near the mining area. The twin tunnels completed before the coal mining activities started were functioning well, but damage was observed after the mining began. Our study reveals the tunnels are located within the InSAR-derived MISA zone, although the tunnels approach the MISA boundary. As direct signs of subsidence, ground fissures have been identified near the tunnels via field investigations and UAV photogrammetry. Furthermore, the derived distribution of ground fissures validates and verifies InSAR measurements. The integrated approach of MT-InSAR, UVA photogrammetry, and field investigation developed in this study can be applied to delineate the irregular boundary of the MISA zone and study the accumulating effects of mining-induced subsidence on the performance of infrastructure in areas proximate to coal mining activities. Full article

(This article belongs to the Special Issue Remote Sensing for Sustainability and Durability of Transportation Infrastructures)

► Show Figures

Figure 1

18 pages, 6544 KB

Open AccessEditor’s ChoiceArticle

Remote Inspection of Bridges with the Integration of Scanning Total Station and Unmanned Aerial Vehicle Data

by Piotr Olaszek, Edgar Maciejewski, Anna Rakoczy, Rafael Cabral, Ricardo Santos and Diogo Ribeiro

Remote Sens. 2024, 16(22), 4176; https://doi.org/10.3390/rs16224176 - 8 Nov 2024

Cited by 16 | Viewed by 3753

Abstract

Remote visual inspections are valuable tools for maintaining bridges in safe operation. In the case of old structures with incomplete documentation, the verification of dimensions is also an essential aspect. This paper presents an attempt to use a Scanning Total Station (STS) and [...] Read more.

Remote visual inspections are valuable tools for maintaining bridges in safe operation. In the case of old structures with incomplete documentation, the verification of dimensions is also an essential aspect. This paper presents an attempt to use a Scanning Total Station (STS) and Unmanned Aerial Vehicle (UAV) for the inspection and inventory of bridge dimensions. The STS’s measurements are conducted by applying two methods: the direct method using a total station (TS) and advanced geometric analyses of the collected point cloud. The UAV’s measurements use a Structure from Motion (SfM) method. Verification tests were conducted on a steel truss railway bridge over the largest river in Poland. The measurements concerned both the basic dimensions of the bridge and the details of a selected truss connection. The STS identified a significant deviation in the actual geometry of the measured connection and the design documentation. The UAV’s inspection confirmed these findings. The integration of STS and UAV technologies has demonstrated significant advantages, including STS’s high accuracy in direct measurements, with deviations within acceptable engineering tolerances (below a few mm), and the UAV’s efficiency in covering large areas, achieving over 90% compliance with reference dimensions. This combined approach not only reduces operating costs and enhances safety by minimizing the need for heavy machinery or scaffolding but also provides a more comprehensive understanding of the structural condition. Full article

(This article belongs to the Special Issue Structural Health Monitoring and Damage Assessment by Advanced Remote Sensing Techniques and Methods)

► Show Figures

Graphical abstract

19 pages, 2630 KB

Open AccessEditor’s ChoiceArticle

Enhancing Long-Term Robustness of Inter-Space Laser Links in Space Gravitational Wave Detection: An Adaptive Weight Optimization Method for Multi-Attitude Sensors Data Fusion

by Zhao Cui, Xue Wang, Jinke Yang, Haoqi Shi, Bo Liang, Xingguang Qian, Zongjin Ye, Jianjun Jia, Yikun Wang and Jianyu Wang

Remote Sens. 2024, 16(22), 4179; https://doi.org/10.3390/rs16224179 - 8 Nov 2024

Cited by 1 | Viewed by 1605

Abstract

The stable and high-precision acquisition of attitude data is crucial for sustaining the long-term robustness of laser links to detect gravitational waves in space. We introduce an effective method that utilizes an adaptive weight optimization approach for the fusion of attitude data obtained [...] Read more.

The stable and high-precision acquisition of attitude data is crucial for sustaining the long-term robustness of laser links to detect gravitational waves in space. We introduce an effective method that utilizes an adaptive weight optimization approach for the fusion of attitude data obtained from charge-coupled device (CCD) spot-positioning-based attitude measurements, differential power sensing (DPS), and differential wavefront sensing (DWS). This approach aims to obtain more robust and lower-noise-level attitude data. A system is designed based on the Michelson interferometer for link simulations; validation experiments are also conducted. The experimental results demonstrate that the fused data exhibit higher robustness. Even in the case of a single sensor failure, valid attitude data can still be obtained. Additionally, the fused data have lower noise levels, with root mean square errors of 9.5%, 37.4%, and 93.4% for the single CCD, DPS, and DWS noise errors, respectively. Full article

(This article belongs to the Special Issue Advances in Multiple Sensor Fusion and Classification for Object Detection and Tracking)

► Show Figures

Figure 1

28 pages, 6037 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Statistical and Independent Component Analysis of Sentinel-1 InSAR Time Series to Assess Land Subsidence Trends

by Celina Anael Farías, Michelle Lenardón Sánchez, Roberta Bonì and Francesca Cigna

Remote Sens. 2024, 16(21), 4066; https://doi.org/10.3390/rs16214066 - 31 Oct 2024

Cited by 14 | Viewed by 6428

Abstract

Advanced statistics can enable the detailed characterization of ground deformation time series, which is a fundamental step for thoroughly understanding the phenomena of land subsidence and their main drivers. This study presents a novel methodological approach based on pre-existing open-access statistical tools to [...] Read more.

Advanced statistics can enable the detailed characterization of ground deformation time series, which is a fundamental step for thoroughly understanding the phenomena of land subsidence and their main drivers. This study presents a novel methodological approach based on pre-existing open-access statistical tools to exploit satellite differential interferometric synthetic aperture radar (DInSAR) data to investigate land subsidence processes, using European Ground Motion Service (EGMS) Sentinel-1 DInSAR 2018−2022 datasets. The workflow involves the implementation of Persistent Scatterers (PS) time series classification through the PS-Time tool, deformation signal decomposition via independent component analysis (ICA), and drivers’ investigation through spatio-temporal correlation with geospatial and monitoring data. Subsidence time series at the three demonstration sites of Bologna, Ravenna and Carpi (Po Plain, Italy) were classified into linear and nonlinear (quadratic, discontinuous, uncorrelated) categories, and the mixed deformation signal of each PS was decomposed into independent components, allowing the identification of new spatial clusters with linear, accelerating/decelerating, and seasonal trends. The relationship between the different independent components and DInSAR-derived displacement velocity, acceleration, and seasonality was also analyzed via regression analysis. Correlation with geological and groundwater monitoring data supported the investigation of the relationship between the observed deformation and subsidence drivers, such as aquifer resource exploitation, local geological setting, and gas extraction/reinjection. Full article

(This article belongs to the Special Issue Monitoring Geohazard from Synthetic Aperture Radar Interferometry)

► Show Figures

Figure 1

32 pages, 7202 KB

Open AccessEditor’s ChoiceArticle

Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation

by Antonio Giganti, Sara Mandelli, Paolo Bestagini and Stefano Tubaro

Remote Sens. 2024, 16(21), 3963; https://doi.org/10.3390/rs16213963 - 24 Oct 2024

Cited by 6 | Viewed by 38799

Abstract

Plants emit biogenic volatile organic compounds (BVOCs), such as isoprene, significantly influencing atmospheric chemistry and climate. BVOC emissions estimated from bottom-up (BU) approaches (derived from numerical simulations) usually exhibit denser and more detailed spatial information compared to those estimated through top-down (TD) approaches [...] Read more.

Plants emit biogenic volatile organic compounds (BVOCs), such as isoprene, significantly influencing atmospheric chemistry and climate. BVOC emissions estimated from bottom-up (BU) approaches (derived from numerical simulations) usually exhibit denser and more detailed spatial information compared to those estimated through top-down (TD) approaches (derived from satellite observations). Moreover, numerically simulated emissions are typically easier to obtain, even if they are less reliable than satellite acquisitions, which, being derived from actual measurements, are considered a more trustworthy instrument for performing chemistry and climate investigations. Given the coarseness and relative lack of satellite-derived measurements, fine-grained numerically simulated emissions could be exploited to enhance them. However, simulated (BU) and observed (TD) emissions usually differ regarding value range and spatiotemporal resolution. In this work, we present a novel deep learning (DL)-based approach to increase the spatial resolution of satellite-derived isoprene emissions, investigating the adoption of efficient domain adaptation (DA) techniques to bridge the gap between numerically simulated emissions and satellite-derived emissions, avoiding the need for retraining a specific super-resolution (SR) algorithm on them. For this, we propose a methodology based on the cycle generative adversarial network (CycleGAN) architecture, which has been extensively used for adapting natural images (like digital photographs) of different domains. In our work, we depart from the standard CycleGAN framework, proposing additional loss terms that allow for better DA and emissions’ SR. We extensively demonstrate the proposed method’s effectiveness and robustness in restoring fine-grained patterns of observed isoprene emissions. Moreover, we compare different setups and validate our approach using different emission inventories from both domains. Eventually, we show that the proposed DA strategy paves the way towards robust SR solutions even in the case of spatial resolution mismatch between the training and testing domains and in the case of unknown testing data. Full article

(This article belongs to the Special Issue Advances in Satellite Image Analysis and Applications for Earth Observation)

► Show Figures

Figure 1

18 pages, 6507 KB

Open AccessEditor’s ChoiceArticle

Estimation of PM_2.5 Using Multi-Angle Polarized TOA Reflectance Data from the GF-5B Satellite

by Ruijie Zhang, Hui Chen, Ruizhi Chen, Chunyan Zhou, Qing Li, Huizhen Xie and Zhongting Wang

Remote Sens. 2024, 16(21), 3944; https://doi.org/10.3390/rs16213944 - 23 Oct 2024

Cited by 7 | Viewed by 2538

Abstract

The use of satellite data to estimate PM_2.5 is an appropriate approach for long-term, substantial monitoring and assessment. To estimate PM_2.5, the majority of the algorithms now in use utilize the top-of-atmosphere (TOA) reflectance or aerosol optical depth (AOD) derived [...] Read more.

The use of satellite data to estimate PM_2.5 is an appropriate approach for long-term, substantial monitoring and assessment. To estimate PM_2.5, the majority of the algorithms now in use utilize the top-of-atmosphere (TOA) reflectance or aerosol optical depth (AOD) derived from scalar satellite data. However, there is relatively little research on the retrieval of PM_2.5 using multi-angle polarized data. With its directional polarimetric camera (DPC), the Chinese new-generation satellite Gaofen 5B (henceforth referred to as GF-5B) offers a unique opportunity to close this gap in multi-angle polarized observation data. In this research, we utilized TOA data from the DPC payload and applied the gradient boosting machine method to simulate the impact of the observation angle, wavelength, and polarization information on the accuracy of PM_2.5 retrieval. We identified the optimal conditions for the effective estimation of PM_2.5. The quantitative results indicated that, under these optimal conditions, the PM_2.5 concentrations retrieved by GF-5B showed a strong correlation with the ground-based data, achieving an R² of 0.9272 and an RMSE of 7.38 µg·m⁻³. By contrast, Himawari-8’s retrieval accuracy under similar data conditions consisted of an R² of 0.9099 and RMSE of 7.42 µg·m⁻³, indicating that GF-5B offers higher accuracy. Furthermore, the retrieval results in this study demonstrated an R² of 0.81 when compared to the CHAP dataset, confirming the feasibility and effectiveness of the use of GF-5B for PM_2.5 retrieval and providing support for PM_2.5 estimation through multi-angle polarized data. Full article

(This article belongs to the Special Issue Trend, Progress and Application of Remote Sensing for Atmospheric Environment and Climate Change)

► Show Figures

Figure 1

21 pages, 7709 KB

Open AccessEditor’s ChoiceArticle

Impacts of GCP Distributions on UAV-PPK Photogrammetry at Sermeq Avannarleq Glacier, Greenland

by Haiyan Zhao, Gang Li, Zhuoqi Chen, Shuhang Zhang, Baogang Zhang and Xiao Cheng

Remote Sens. 2024, 16(21), 3934; https://doi.org/10.3390/rs16213934 - 22 Oct 2024

Cited by 9 | Viewed by 3460

Abstract

Real-Time/Post-Processing Kinematic (RTK/PPK) technology has been widely applied in Unmanned Aerial Vehicle (UAV) photogrammetry in glaciological research. Considering that ground control points (GCPs) cannot be set on glaciers, evaluating the impacts of one-sided distribution is essential. In this study, 8571 images were captured [...] Read more.

Real-Time/Post-Processing Kinematic (RTK/PPK) technology has been widely applied in Unmanned Aerial Vehicle (UAV) photogrammetry in glaciological research. Considering that ground control points (GCPs) cannot be set on glaciers, evaluating the impacts of one-sided distribution is essential. In this study, 8571 images were captured at Sermeq Avannarleq glacier in western Greenland from 4 August 2021 to the 6th, covering approximately 85 km², with the furthest distance being 13.22 km away from the coastline. Benefited by the meandering coastline, 11 roving stations roughly uniformly distributed on bare rock were surveyed with the RTK technique. PPK-geotagged images were processed in Agisoft Metashape Professional to derive the DSMs, utilizing eight different configurations of GCP distributions that gradually extended longitudinally (along the glacier flow direction) to the upper part of the glacier. The accuracy of DSMs was evaluated by referring to the validation points (VPs) that were not employed in the Bundle Block Adjustment (BBA). The results indicated that the RMSE values of the easting, northing, and height of the reconstruction model georeferenced by only PPK geotagging (no GCPs applied) were 0.038 m, 0.031 m, and 0.146 m, respectively. Applying four GCPs located at one side of the region but with both longitudinal and lateral distribution improved the RMSE values in easting, northing, and vertical to 0.037 m, 0.031 m, and 0.081 m, respectively, and these values were stable even when distributing four GCPs evenly or when increasing the number of GCPs to eleven. Moreover, the cross-validation with ICESat-2 and ArcticDEM performed only at an off-glacier region also suggested that vertical accuracy shows significant improvements for every configuration of GCPs compared to the reconstruction model optimized only by PPK, but such improvements were not obvious if the number of GCPs exceeded four. Moreover, no elevation ramps appeared in the UAV DSM, even for the GCP configuration with only two GCPs distributed at the terminus. Therefore, combining PPK with only a few GCPs but distributing in both directions of the surveying region can offer a viable solution for obtaining glacier DSMs at the coastline with decimeter-level accuracy. Full article

(This article belongs to the Special Issue Earth Observation of Glacier and Snow Cover Mapping in Cold Regions)

► Show Figures

Graphical abstract

27 pages, 31281 KB

Open AccessEditor’s ChoiceArticle

Tracking Moisture Dynamics in a Karst Rock Formation Combining Multi-Frequency 3D GPR Data: A Strategy for Protecting the Polychrome Hall Paintings in Altamira Cave

by Vicente Bayarri, Alfredo Prada, Francisco García, Carmen De Las Heras and Pilar Fatás

Remote Sens. 2024, 16(20), 3905; https://doi.org/10.3390/rs16203905 - 21 Oct 2024

Cited by 5 | Viewed by 3359

Abstract

This study addresses the features of the internal structure of the geological layers adjacent to the Polychrome Hall ceiling of the Cave of Altamira (Spain) and their link to the distribution of moisture and geological discontinuities mainly as fractures, joints, bedding planes and [...] Read more.

This study addresses the features of the internal structure of the geological layers adjacent to the Polychrome Hall ceiling of the Cave of Altamira (Spain) and their link to the distribution of moisture and geological discontinuities mainly as fractures, joints, bedding planes and detachments, using 3D Ground Penetrating Radar (GPR) mapping. In this research, 3D GPR data were collected with 300 MHz, 800 MHz and 1.6 GHz center frequency antennas. The data recorded with these three frequency antennas were combined to further our understanding of the layout of geological discontinuities and how they link to the moisture or water inputs that infiltrate and reach the ceiling surface where the rock art of the Polychrome Hall is located. The same 1 × 1 m² area was adopted for 3D data acquisition with the three antennas, obtaining 3D isosurface (isoattribute-surface) images of internal distribution of moisture and structural features of the Polychrome Hall ceiling. The results derived from this study reveal significant insights into the overlying karst strata of Polychrome Hall, particularly the interface between the Polychrome Layer and the underlying Dolomitic Layer. The results show moisture patterns associated with geological features such as fractures, joints, detachments of strata and microcatchments, elucidating the mechanisms driving capillary rise and water infiltration coming from higher altitudes. The study primarily identifies areas of increased moisture content, correlating with earlier observations and enhancing our understanding of water infiltration patterns. This underscores the utility of 3D GPR as an essential tool for informing and putting conservation measures into practice. By delineating subsurface structures and moisture dynamics, this research contributes to a deeper analysis of the deterioration processes directly associated with the infiltration water both in this ceiling and in the rest of the Cave of Altamira, providing information to determine its future geological and hydrogeological evolution. Full article

(This article belongs to the Special Issue Multi-Data Applied to Near-Surface Geophysics (Second Edition))

► Show Figures

Figure 1

34 pages, 8862 KB

Open AccessEditor’s ChoiceArticle

A Novel Detection Transformer Framework for Ship Detection in Synthetic Aperture Radar Imagery Using Advanced Feature Fusion and Polarimetric Techniques

by Mahmoud Ahmed, Naser El-Sheimy and Henry Leung

Remote Sens. 2024, 16(20), 3877; https://doi.org/10.3390/rs16203877 - 18 Oct 2024

Cited by 18 | Viewed by 5046

Abstract

Ship detection in synthetic aperture radar (SAR) imagery faces significant challenges due to the limitations of traditional methods, such as convolutional neural network (CNN) and anchor-based matching approaches, which struggle with accurately detecting smaller targets as well as adapting to varying environmental conditions. [...] Read more.

Ship detection in synthetic aperture radar (SAR) imagery faces significant challenges due to the limitations of traditional methods, such as convolutional neural network (CNN) and anchor-based matching approaches, which struggle with accurately detecting smaller targets as well as adapting to varying environmental conditions. These methods, relying on either intensity values or single-target characteristics, often fail to enhance the signal-to-clutter ratio (SCR) and are prone to false detections due to environmental factors. To address these issues, a novel framework is introduced that leverages the detection transformer (DETR) model along with advanced feature fusion techniques to enhance ship detection. This feature enhancement DETR (FEDETR) module manages clutter and improves feature extraction through preprocessing techniques such as filtering, denoising, and applying maximum and median pooling with various kernel sizes. Furthermore, it combines metrics like the line spread function (LSF), peak signal-to-noise ratio (PSNR), and F1 score to predict optimal pooling configurations and thus enhance edge sharpness, image fidelity, and detection accuracy. Complementing this, the weighted feature fusion (WFF) module integrates polarimetric SAR (PolSAR) methods such as Pauli decomposition, coherence matrix analysis, and feature volume and helix scattering (Fvh) components decomposition, along with FEDETR attention maps, to provide detailed radar scattering insights that enhance ship response characterization. Finally, by integrating wave polarization properties, the ability to distinguish and characterize targets is augmented, thereby improving SCR and facilitating the detection of weakly scattered targets in SAR imagery. Overall, this new framework significantly boosts DETR’s performance, offering a robust solution for maritime surveillance and security. Full article

(This article belongs to the Special Issue Target Detection with Fully-Polarized Radar)

► Show Figures

Graphical abstract

24 pages, 15074 KB

Open AccessEditor’s ChoiceArticle

The Standardized Spectroscopic Mixture Model

by Christopher Small and Daniel Sousa

Remote Sens. 2024, 16(20), 3768; https://doi.org/10.3390/rs16203768 - 11 Oct 2024

Cited by 8 | Viewed by 2379

Abstract

The standardized spectral mixture model combines the specificity of a physically based representation of a spectrally mixed pixel with the generality and portability of a spectral index. Earlier studies have used spectrally and geographically diverse collections of broadband and spectroscopic imagery to show [...] Read more.

The standardized spectral mixture model combines the specificity of a physically based representation of a spectrally mixed pixel with the generality and portability of a spectral index. Earlier studies have used spectrally and geographically diverse collections of broadband and spectroscopic imagery to show that the reflectance of the majority of ice-free landscapes on Earth can be represented as linear mixtures of rock and soil substrates (S), photosynthetic vegetation (V) and dark targets (D) composed of shadow and spectrally absorptive/transmissive materials. However, both broadband and spectroscopic studies of the topology of spectral mixing spaces raise questions about the completeness and generality of the Substrate, Vegetation, Dark (SVD) model for imaging spectrometer data. This study uses a spectrally diverse collection of 40 granules from the EMIT imaging spectrometer to verify the generality and stability of the spectroscopic SVD model and characterize the SVD topology and plane of substrates to assess linearity of spectral mixing. New endmembers for soil and non-photosynthetic vegetation (NPV; N) allow the planar SVD model to be extended to a tetrahedral SVDN model to better accommodate the 3D topology of the mixing space. The SVDN model achieves smaller misfit than the SVD, but does so at the expense of implausible fractions beyond [0, 1]. However, a refined spectroscopic SVD model still achieves small (<0.03) RMS misfit, negligible sensitivity to endmember variability and strongly linear scaling over more than an order of magnitude range of spatial resolution. Full article

(This article belongs to the Special Issue New Advancements in the Field of Remote Sensing in Land Surface Processes)

► Show Figures

Figure 1

23 pages, 32897 KB

Open AccessEditor’s ChoiceArticle

On the Suitability of Different Satellite Land Surface Temperature Products to Study Surface Urban Heat Islands

by Alexandra Hurduc, Sofia L. Ermida and Carlos C. DaCamara

Remote Sens. 2024, 16(20), 3765; https://doi.org/10.3390/rs16203765 - 10 Oct 2024

Cited by 20 | Viewed by 6226

Abstract

Remote sensing satellite data have been a crucial tool in understanding urban climates. The variety of sensors with different spatiotemporal characteristics and retrieval methodologies gave rise to a multitude of approaches when analyzing the surface urban heat island effect (SUHI). Although there are [...] Read more.

Remote sensing satellite data have been a crucial tool in understanding urban climates. The variety of sensors with different spatiotemporal characteristics and retrieval methodologies gave rise to a multitude of approaches when analyzing the surface urban heat island effect (SUHI). Although there are considerable advantages that arise from these different characteristics (spatiotemporal resolution, time of observation, etc.), it also means that there is a need for understanding the ability of sensors in capturing spatial and temporal SUHI patterns. For this, several land surface temperature products are compared for the cities of Madrid and Paris, retrieved from five sensors: the Spinning Enhanced Visible and InfraRed Imager onboard Meteosat Second Generation, the Advanced Very-High-Resolution Radiometer onboard Metop, the Moderate-resolution Imaging Spectroradiometer onboard both Aqua and Terra, and the Thermal Infrared Sensor onboard Landsat 8 and 9. These products span a wide range of LST algorithms, including split-window, single-channel, and temperature–emissivity separation methods. Results show that the diurnal amplitude of SUHI may not be well represented when considering daytime and nighttime polar orbiting platforms. Also, significant differences arise in SUHI intensity and spatial and temporal variability due to the different methods implemented for LST retrieval. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

21 pages, 6212 KB

Open AccessEditor’s ChoiceArticle

Validation and Error Minimization of Global Ecosystem Dynamics Investigation (GEDI) Relative Height Metrics in the Amazon

by Alyson East, Andrew Hansen, Patrick Jantz, Bryce Currey, David W. Roberts and Dolors Armenteras

Remote Sens. 2024, 16(19), 3550; https://doi.org/10.3390/rs16193550 - 24 Sep 2024

Cited by 11 | Viewed by 4936

Abstract

Global Ecosystem Dynamics Investigation (GEDI) is a relatively new technology for global forest research, acquiring LiDAR measurements of vertical vegetation structure across Earth’s tropical, sub-tropical, and temperate forests. Previous GEDI validation efforts have largely focused on top of canopy accuracy, and findings vary [...] Read more.

Global Ecosystem Dynamics Investigation (GEDI) is a relatively new technology for global forest research, acquiring LiDAR measurements of vertical vegetation structure across Earth’s tropical, sub-tropical, and temperate forests. Previous GEDI validation efforts have largely focused on top of canopy accuracy, and findings vary by geographic region and forest type. Despite this, many applications utilize measurements of vertical vegetation distribution from the lower canopy, with a wide diversity of uses for GEDI data appearing in the literature. Given the variability in data requirements across research applications and ecosystems, and the regional variability in GEDI data quality, it is imperative to understand GEDI error to draw strong inferences. Here, we quantify the accuracy of GEDI relative height metrics through canopy layers for the Brazilian Amazon. To assess the accuracy of on-orbit GEDI L2A relative height metrics, we utilize the GEDI waveform simulator to compare detailed airborne laser scanning (ALS) data from the Sustainable Landscapes Brazil project to GEDI data collected by the International Space Station. We also assess the impacts of data filtering based on biophysical and GEDI sensor conditions and geolocation correction on GEDI error metrics (RMSE, MAE, and Bias) through canopy levels. GEDI data accuracy attenuates through the lower percentiles in the relative height (RH) curve. While top of canopy (RH₉₈) measurements have relatively high accuracy (R² = 0.76, RMSE = 5.33 m), the accuracy of data decreases lower in the canopy (RH₅₀: R² = 0.54, RMSE = 5.59 m). While simulated geolocation correction yielded marginal improvements, this decrease in accuracy remained constant despite all error reduction measures. Some error rates for the Amazon are double those reported in studies from other regions. These findings have broad implications for the application of GEDI data, especially in studies where forest understory measurements are particularly challenging to acquire (e.g., dense tropical forests) and where understory accuracy is highly important. Full article

► Show Figures

Figure 1

15 pages, 4826 KB

Open AccessEditor’s ChoiceArticle

Assessing Evapotranspiration Changes in Response to Cropland Expansion in Tropical Climates

by Leonardo Laipelt, Julia Brusso Rossi, Bruno Comini de Andrade, Morris Scherer-Warren and Anderson Ruhoff

Remote Sens. 2024, 16(18), 3404; https://doi.org/10.3390/rs16183404 - 13 Sep 2024

Cited by 3 | Viewed by 3320

Abstract

The expansion of cropland in tropical regions has significantly accelerated in recent decades, triggering an escalation in water demand and changing the total water loss to the atmosphere (evapotranspiration). Additionally, the increase in areas dedicated to agriculture in tropical climates coincides with an [...] Read more.

The expansion of cropland in tropical regions has significantly accelerated in recent decades, triggering an escalation in water demand and changing the total water loss to the atmosphere (evapotranspiration). Additionally, the increase in areas dedicated to agriculture in tropical climates coincides with an increased frequency of drought events, leading to a series of conflicts among water users. However, detailed studies on the impacts of changes in water use due to agriculture expansion, including irrigation, are still lacking. Furthermore, the higher presence of clouds in tropical environments poses challenges for the availability of high-resolution data for vegetation monitoring via satellite images. This study aims to analyze 37 years of agricultural expansion using the Landsat collection and a satellite-based model (geeSEBAL) to assess changes in evapotranspiration resulting from cropland expansion in tropical climates, focusing on the São Marcos River Basin in Brazil. It also used a methodology for estimating daily evapotranspiration on days without satellite images. The results showed a 34% increase in evapotranspiration from rainfed areas, mainly driven by soybean cultivation. In addition, irrigated areas increased their water use, despite not significantly changing water use at the basin scale. Conversely, natural vegetation areas decreased their evapotranspiration rates by 22%, suggesting possible further implications with advancing changes in land use and land cover. Thus, this study underscores the importance of using satellite-based evapotranspiration estimates to enhance our understanding of water use across different land use types and scales, thereby improving water management strategies on a large scale. Full article

(This article belongs to the Special Issue Remote Sensing for Agricultural Water Management (RSAWM) (Second Edition))

► Show Figures

Figure 1

28 pages, 20281 KB

Open AccessEditor’s ChoiceArticle

Spatiotemporal Prediction of Conflict Fatality Risk Using Convolutional Neural Networks and Satellite Imagery

by Seth Goodman, Ariel BenYishay and Daniel Runfola

Remote Sens. 2024, 16(18), 3411; https://doi.org/10.3390/rs16183411 - 13 Sep 2024

Cited by 6 | Viewed by 3483

Abstract

As both satellite imagery and image-based machine learning methods continue to improve and become more accessible, they are being utilized in an increasing number of sectors and applications. Recent applications using convolutional neural networks (CNNs) and satellite imagery include estimating socioeconomic and development [...] Read more.

As both satellite imagery and image-based machine learning methods continue to improve and become more accessible, they are being utilized in an increasing number of sectors and applications. Recent applications using convolutional neural networks (CNNs) and satellite imagery include estimating socioeconomic and development indicators such as poverty, road quality, and conflict. This article builds on existing work leveraging satellite imagery and machine learning for estimation or prediction, to explore the potential to extend these methods temporally. Using Landsat 8 imagery and data from the Armed Conflict Location & Event Data Project (ACLED) we produce subnational predictions of the risk of conflict fatalities in Nigeria during 2015, 2017, and 2019 using distinct models trained on both yearly and six-month windows of data from the preceding year. We find that predictions at conflict sites leveraging imagery from the preceding year for training can predict conflict fatalities in the following year with an area under the receiver operating characteristic curve (AUC) of over 75% on average. While models consistently outperform a baseline comparison, and performance in individual periods can be strong (AUC > 80%), changes based on ground conditions such as the geographic scope of conflict can degrade performance in subsequent periods. In addition, we find that training models using an entire year of data slightly outperform models using only six months of data. Overall, the findings suggest CNN-based methods are moderately effective at detecting features in Landsat satellite imagery associated with the risk of fatalities from conflict events across time periods. Full article

(This article belongs to the Special Issue Weakly Supervised Deep Learning in Exploiting Remote Sensing Big Data)

► Show Figures

Figure 1

29 pages, 6780 KB

Open AccessEditor’s ChoiceArticle

Phenological and Biophysical Mediterranean Orchard Assessment Using Ground-Based Methods and Sentinel 2 Data

by Pierre Rouault, Dominique Courault, Guillaume Pouget, Fabrice Flamain, Papa-Khaly Diop, Véronique Desfonds, Claude Doussan, André Chanzy, Marta Debolini, Matthew McCabe and Raul Lopez-Lozano

Remote Sens. 2024, 16(18), 3393; https://doi.org/10.3390/rs16183393 - 12 Sep 2024

Cited by 9 | Viewed by 4430

Abstract

A range of remote sensing platforms provide high spatial and temporal resolution insights which are useful for monitoring vegetation growth. Very few studies have focused on fruit orchards, largely due to the inherent complexity of their structure. Fruit trees are mixed with inter-rows [...] Read more.

A range of remote sensing platforms provide high spatial and temporal resolution insights which are useful for monitoring vegetation growth. Very few studies have focused on fruit orchards, largely due to the inherent complexity of their structure. Fruit trees are mixed with inter-rows that can be grassed or non-grassed, and there are no standard protocols for ground measurements suitable for the range of crops. The assessment of biophysical variables (BVs) for fruit orchards from optical satellites remains a significant challenge. The objectives of this study are as follows: (1) to address the challenges of extracting and better interpreting biophysical variables from optical data by proposing new ground measurements protocols tailored to various orchards with differing inter-row management practices, (2) to quantify the impact of the inter-row at the Sentinel pixel scale, and (3) to evaluate the potential of Sentinel 2 data on BVs for orchard development monitoring and the detection of key phenological stages, such as the flowering and fruit set stages. Several orchards in two pedo-climatic zones in southeast France were monitored for three years: four apricot and nectarine orchards under different management systems and nine cherry orchards with differing tree densities and inter-row surfaces. We provide the first comparison of three established ground-based methods of assessing BVs in orchards: (1) hemispherical photographs, (2) a ceptometer, and (3) the Viticanopy smartphone app. The major phenological stages, from budburst to fruit growth, were also determined by in situ annotations on the same fields monitored using Viticanopy. In parallel, Sentinel 2 images from the two study sites were processed using a Biophysical Variable Neural Network (BVNET) model to extract the main BVs, including the leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fraction of green vegetation cover (FCOVER). The temporal dynamics of the normalised FAPAR were analysed, enabling the detection of the fruit set stage. A new aggregative model was applied to data from hemispherical photographs taken under trees and within inter-rows, enabling us to quantify the impact of the inter-row at the Sentinel 2 pixel scale. The resulting value compared to BVs computed from Sentinel 2 gave statistically significant correlations (0.57 for FCOVER and 0.45 for FAPAR, with respective RMSE values of 0.12 and 0.11). Viticanopy appears promising for assessing the PAI (plant area index) and FCOVER for orchards with grassed inter-rows, showing significant correlations with the Sentinel 2 LAI (R² of 0.72, RMSE 0.41) and FCOVER (R² 0.66 and RMSE 0.08). Overall, our results suggest that Sentinel 2 imagery can support orchard monitoring via indicators of development and inter-row management, offering data that are useful to quantify production and enhance resource management. Full article

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)

► Show Figures

Figure 1

19 pages, 7218 KB

Open AccessEditor’s ChoiceArticle

Relationship between Vegetation and Soil Moisture Anomalies Based on Remote Sensing Data: A Semiarid Rangeland Case

by Juan José Martín-Sotoca, Ernesto Sanz, Antonio Saa-Requejo, Rubén Moratiel, Andrés F. Almeida-Ñauñay and Ana M. Tarquis

Remote Sens. 2024, 16(18), 3369; https://doi.org/10.3390/rs16183369 - 11 Sep 2024

Cited by 9 | Viewed by 3856

Abstract

The dynamic of rangelands results from complex interactions between vegetation, soil, climate, and human activity. This scenario makes rangeland’s condition challenging to monitor, and degradation assessment should be carefully considered when studying grazing pressures. In the present work, we study the interaction of [...] Read more.

The dynamic of rangelands results from complex interactions between vegetation, soil, climate, and human activity. This scenario makes rangeland’s condition challenging to monitor, and degradation assessment should be carefully considered when studying grazing pressures. In the present work, we study the interaction of vegetation and soil moisture in semiarid rangelands using vegetation and soil moisture indices. We aim to study the feasibility of using soil moisture negative anomalies as a warning index for vegetation or agricultural drought. Two semiarid agricultural regions were selected in Spain for this study: Los Vélez (Almería) and Bajo Aragón (Teruel). MODIS images, with 250 m and 500 m spatial resolution, from 2002 to 2019, were acquired to calculate the Vegetation Condition Index (VCI) and the Water Condition Index (WCI) based on the Normalised Difference Vegetation Index (NDVI) and soil moisture component (W), respectively. The Optical Trapezoid Model (OPTRAM) estimated this latter W index. From them, the anomaly (Z-score) for each index was calculated, being

Z_{V C I}

and

Z_{W C I}

, respectively. The probability of coincidence of their negative anomalies was calculated every 10 days (10-day periods). The results show that for specific months, the

Z_{W C I}

had a strong probability of informing in advance, where the negative

Z_{V C I}

will decrease. Soil moisture content and vegetation indices show more similar dynamics in the months with lower temperatures (from autumn to spring). In these months, given the low temperatures, precipitation leads to vegetation growth. In the following months, water availability depends on evapotranspiration and vegetation type as the temperature rises and the precipitation falls. The stronger relationship between vegetation and precipitation from autumn to the beginning of spring is reflected in the feasibility of

Z_{W C I}

to aid the prediction of

Z_{V C I}

. During these months, using

Z_{W C I}

as a warning index is possible for both areas studied. Notably, November to the beginning of February showed an average increase of 20–30% in the predictability of vegetation anomalies, knowing moisture soil anomalies four lags in advance. We found other periods of relevant increment in the predictability, such as March and April for Los Vélez, and from July to September for Bajo Aragón. Full article

(This article belongs to the Special Issue Advances in Remote Sensing for Regional Soil Moisture Monitoring)

► Show Figures

Figure 1

16 pages, 10159 KB

Open AccessEditor’s ChoiceArticle

Contribution of Climatic Change and Human Activities to Vegetation Dynamics over Southwest China during 2000–2020

by Gang Qi, Nan Cong, Man Luo, Tangzhen Qiu, Lei Rong, Ping Ren and Jiangtao Xiao

Remote Sens. 2024, 16(18), 3361; https://doi.org/10.3390/rs16183361 - 10 Sep 2024

Cited by 9 | Viewed by 8129

Abstract

Southwest China is an important carbon sink area in China. It is critical to track and assess how human activity (HA) and climate change (CC) affect plant alterations in order to create effective and sustainable vegetation restoration techniques. This study used MODIS NDVI [...] Read more.

Southwest China is an important carbon sink area in China. It is critical to track and assess how human activity (HA) and climate change (CC) affect plant alterations in order to create effective and sustainable vegetation restoration techniques. This study used MODIS NDVI data, vegetation type data, and meteorological data to examine the regional and temporal variations in the normalized difference vegetation index (NDVI) in Southwest China from 2000 to 2020. Using trend analysis, the study looks at the temporal and geographical variability in the NDVI. Partial correlation analysis was also used to assess the effects of precipitation, extreme climate indicators, and mean temperature on the dynamics of the vegetation. A new residual analysis technique was created to categorize the effects of CC and HA on NDVI changes while taking extreme climate into consideration. The findings showed that the NDVI in Southwest China grew at a rate of 0.02 per decade between 2000 and 2020. According to the annual NDVI, there was a regional rise in around 85.59% of the vegetative areas, with notable increases in 36.34% of these regions. Temperature had a major influence on the northern half of the research region, but precipitation and extreme climate had a notable effect on the southern half. The rates at which climatic variables and human activity contributed to changes in the NDVI were 0.0008/10a and 0.0034/10a, respectively. These rates accounted for 19.1% and 80.9% of the variances, respectively. The findings demonstrate that most areas displayed greater HA-induced NDVI increases, with the exception of the western Sichuan Plateau. This result suggests that when formulating vegetation restoration and conservation strategies, special attention should be paid to the impact of human activities on vegetation to ensure the sustainable development of ecosystems. Full article

(This article belongs to the Special Issue Quantitative Remote Sensing for Vegetation Phenology and Regional Landscape Patterns)

► Show Figures

Figure 1

18 pages, 232655 KB

Open AccessEditor’s ChoiceArticle

SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation

by Gyutae Hwang, Jiwoo Jeong and Sang Jun Lee

Remote Sens. 2024, 16(17), 3278; https://doi.org/10.3390/rs16173278 - 3 Sep 2024

Cited by 39 | Viewed by 6696

Abstract

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual [...] Read more.

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M. Full article

(This article belongs to the Special Issue Deep Learning for Remote Sensing and Geodata)

► Show Figures

Figure 1

31 pages, 5838 KB

Open AccessEditor’s ChoiceReview

Monitoring Heavy Metals and Metalloids in Soils and Vegetation by Remote Sensing: A Review

by Viktoriia Lovynska, Bagher Bayat, Roland Bol, Shirin Moradi, Mehdi Rahmati, Rahul Raj, Svitlana Sytnyk, Oliver Wiche, Bei Wu and Carsten Montzka

Remote Sens. 2024, 16(17), 3221; https://doi.org/10.3390/rs16173221 - 30 Aug 2024

Cited by 57 | Viewed by 14568

Abstract

Heavy metal contamination in soils and vegetation poses a significant problem due to its toxicity and persistence. Toxic effects on vegetation include not only impaired growth, reduced yields, and even plant death but also biodiversity loss and ecosystem degradation. Addressing this issue requires [...] Read more.

Heavy metal contamination in soils and vegetation poses a significant problem due to its toxicity and persistence. Toxic effects on vegetation include not only impaired growth, reduced yields, and even plant death but also biodiversity loss and ecosystem degradation. Addressing this issue requires comprehensive monitoring and remediation efforts to mitigate the environmental, human health, and ecological impacts. This review examines the state-of-the-art methodologies and advancements in remote sensing applications for detecting and monitoring heavy metal contamination in soil and its subsequent effects on vegetation. By synthesizing the current research findings and technological developments, this review offers insights into the efficacy and potential of remote sensing for monitoring heavy metal contamination in terrestrial ecosystems. However, current studies focus on regression and AI methods to link spectral reflectances and indices to heavy metal concentrations, which poses limited transferability to other areas, times, spectral discretizations, and heavy metal elements. We conclude that one important way forward is the more thorough understanding and simulation of the related physico-chemical processes in soils and plants and their effects on the spectral signatures. This would offer a profound basis for remote sensing applications for individual circumstances and would allow disentangling heavy metal effects from other stressors such as droughts or soil salinity. Full article

(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI