Remote Sensing

30 pages, 8161 KiB

Open AccessArticle

A Three-Dimensional FDTD(2,4) Subgridding Algorithm for the Airborne Ground-Penetrating Radar Detection of Landslide Models

by Lifeng Mao, Xuben Wang, Yuelong Chi, Su Pang, Xiangpeng Wang and Qilin Huang

Remote Sens. 2025, 17(6), 1107; https://doi.org/10.3390/rs17061107 - 20 Mar 2025

Viewed by 292

Abstract

The finite-difference time-domain (FDTD) method is a robust numerical approach for the three-dimensional forward modeling of airborne ground-penetrating radar responses of complex geological structures, particularly landslides. However, standard FDTD implementations encounter significant memory demands as aircraft altitude increases and when modeling high-permittivity subsurface [...] Read more.

The finite-difference time-domain (FDTD) method is a robust numerical approach for the three-dimensional forward modeling of airborne ground-penetrating radar responses of complex geological structures, particularly landslides. However, standard FDTD implementations encounter significant memory demands as aircraft altitude increases and when modeling high-permittivity subsurface media (e.g., water-saturated soils), often exceeding ordinary computational resources. Existing subgridding FDTD methods, tailored for simple localized target models, are also inadequate for simulating landslide models. To overcome these limitations, we thus propose a novel high-order FDTD-based subgridding algorithm that applies coarse grids to the air layer and fine grids to the subsurface medium, enabling the simulation of arbitrarily complex landslide models with significantly reduced memory consumption. This study achieves the first implementation of the high-order FDTD(2,4) method in both coarse- and fine-grid regions, which enables larger grid sizes in both regions. As a result, the proposed approach not only preserves high-order spatial accuracy but also achieves significant memory savings. To mitigate the challenges posed by higher-order difference stencils, we introduce a specialized grid configuration with an overlap zone between coarse and fine grids, supplemented by surrounding virtual nodes. The algorithm accommodates various grid refinement factors, ensuring adaptability to dielectric models with diverse permittivity values and structural complexities. By optimizing the grid refinement factor based on the subsurface medium’s maximum permittivity, simulations can be performed with minimal memory usage. Field updates within the overlapping region are followed by weighted corrections to ensure numerical stability, whereas simulations without these novel measures exhibit oscillatory artifacts. Wavefield snapshots reveal seamless transitions across grid boundaries without spurious artifacts. Numerical experiments on deposition-type landslide models and water-bearing media confirm the validity and stability of the proposed method. Notably, using the optimal grid refinement factor reduces memory consumption to less than 8% of the standard FDTD method for aquifer model simulations. Full article

► Show Figures

Figure 1

22 pages, 8459 KiB

Open AccessArticle

Integrating InSAR Data and LE-Transformer for Foundation Pit Deformation Prediction

by Bo Hu, Wen Li, Weifeng Lu, Feilong Zhao, Yuebin Li and Rijun Li

Remote Sens. 2025, 17(6), 1106; https://doi.org/10.3390/rs17061106 - 20 Mar 2025

Viewed by 285

Abstract

The rapid development of urban infrastructure has accelerated the construction of large foundation pit projects, posing challenges for deformation monitoring and safety. This study proposes a novel approach integrating time-series InSAR data with a multivariate LE-Transformer model for deformation prediction. The LE-Transformer model [...] Read more.

The rapid development of urban infrastructure has accelerated the construction of large foundation pit projects, posing challenges for deformation monitoring and safety. This study proposes a novel approach integrating time-series InSAR data with a multivariate LE-Transformer model for deformation prediction. The LE-Transformer model integrates Long Short-Term Memory (LSTM) to capture temporal dependencies, Efficient Additive Attention (EAA) to reduce computational complexity, and Transformer mechanisms to model global data relationships. Deformation monitoring was performed using PS-InSAR and SBAS-InSAR techniques, showing a high correlation coefficient (0.92), confirming the reliability of the data. Gray relational analysis identified key influencing factors, including rainfall, subway construction, residential buildings, soil temperature, and hydrogeology, with rainfall being the most significant (correlation of 0.838). These factors were incorporated into the LE-Transformer model, which outperformed univariate models, achieving a mean absolute percentage error (MAPE) of 2.5%. This approach provides a robust framework for deformation prediction and early warning systems in urban infrastructure projects. Full article

(This article belongs to the Special Issue Latest Improvements and Applications of Ground Deformation Monitoring Based on Remote Sensing Data (Second Edition))

► Show Figures

Figure 1

23 pages, 44374 KiB

Open AccessArticle

Evaluation and Optimization Strategies for Forest Landscape Stability in Different Landform Types of the Loess Plateau

by Mei Zhang, Peng Liu and Zhong Zhao

Remote Sens. 2025, 17(6), 1105; https://doi.org/10.3390/rs17061105 - 20 Mar 2025

Viewed by 242

Abstract

This study aims to develop a forest landscape stability assessment framework that integrates structure, function, and resilience to assess forest landscape stability under different landform types on the Loess Plateau, and to propose differentiated optimization strategies. Remote sensing images and ground survey data [...] Read more.

This study aims to develop a forest landscape stability assessment framework that integrates structure, function, and resilience to assess forest landscape stability under different landform types on the Loess Plateau, and to propose differentiated optimization strategies. Remote sensing images and ground survey data were combined to compare the effectiveness of different machine learning models in aboveground biomass (AGB) inversion. Meanwhile, forest fragmentation and landscape multifunctionality were assessed, and a Landscape Stability Index (LSI) was proposed to quantify regional forest landscape stability. The main findings are as follows: (1) between 2000 and 2022, the degree of forest fragmentation and multifunctionality in the hilly gully region improved significantly, and the Simpson’s Diversity Index (SDI) value showed an increasing trend; the plateau gully region showed a decreasing trend in the SDI value. The degree of forest fragmentation in the hilly gully region was higher and showed significant changes, while the plateau gully region was more stable, with the “Interior” and “Dominant” types dominating. (2) The eXtreme Gradient Boosting model outperformed other models in AGB estimation, with R² = 0.81 and RMSE = 24.67 ton ha⁻¹. (3) The LSI of the hilly gully region generally increased, especially in Yanchang, showing a significant increase in ecological stability; the LSI of the plateau gully region generally decreased, especially in Baishui, showing a trend of weakening stability. Based on the assessment results, optimization strategies for different stabilities were proposed, including the hierarchical management of fragmentation, multi-objective management to improve the SDI, and adaptive management for AGB. The forest landscape stability assessment framework proposed in this study can effectively assess the stability of forest landscapes, reveal the differences in ecological restoration in different regions, and provide new perspectives and strategies for forest landscape management and optimization in the Loess Plateau. Full article

► Show Figures

Figure 1

20 pages, 12169 KiB

Open AccessArticle

Exploring the Advantages of Multi-GNSS Ionosphere-Weighted Single-Frequency Precise Point Positioning in Regional Ionospheric VTEC Modeling

by Ahao Wang, Yize Zhang, Junping Chen, Hu Wang, Xuexi Liu, Yihang Xu, Jing Li and Yuyan Yan

Remote Sens. 2025, 17(6), 1104; https://doi.org/10.3390/rs17061104 - 20 Mar 2025

Viewed by 190

Abstract

Although the traditional Carrier-to-Code Leveling (CCL) method can provide ideal slant total electron content (STEC) observables for establishing ionospheric models, it must rely on dual-frequency (DF) receivers, which results in high hardware costs. In this study, an ionosphere-weight (IW) single-frequency (SF) precise point [...] Read more.

Although the traditional Carrier-to-Code Leveling (CCL) method can provide ideal slant total electron content (STEC) observables for establishing ionospheric models, it must rely on dual-frequency (DF) receivers, which results in high hardware costs. In this study, an ionosphere-weight (IW) single-frequency (SF) precise point positioning (PPP) method for extracting STEC observables is proposed, and multi-global navigation satellite system (GNSS)-integrated processing is adopted to improve the spatial resolution of the ionospheric model. To investigate the advantages of this novel method, 41 European stations are used to establish the regional ionospheric model, and both low- and high-solar-activity conditions are considered. The results show that the IW SFPPP-derived regional ionospheric model has a significantly better quality of vertical total electron content (VTEC) than the CCL method when using the final global ionospheric map (GIM) as a reference, especially in areas with sparse monitoring stations. Compared with the CCL method, the RMS VTEC accuracy of the IW SFPPP method can be improved by 17.4% and 12.7% to 1.09 and 2.83 total electron content unit (TECU) in low- and high-solar-activity periods, respectively. Regarding GNSS carrier-phase-derived STEC variation (dSTEC) as the reference, the dSTEC accuracy of the IW SFPPP method is comparable to that of the CCL method, and its RMS values are about 1.5 and 2.8 TECU in low- and high-solar-activity conditions, respectively. This indicates that the proposed method using SF-only observations can achieve the same external accord accuracy as the CCL method in regional ionospheric modeling. Full article

(This article belongs to the Special Issue Advanced Multi-GNSS Positioning and Its Applications in Geoscience)

► Show Figures

Figure 1

18 pages, 4206 KiB

Open AccessArticle

EOST-LSTM: Long Short-Term Memory Model Combined with Attention Module and Full-Dimensional Dynamic Convolution Module

by Guangxin He, Wei Wu, Jing Han, Jingjia Luo and Lei Lei

Remote Sens. 2025, 17(6), 1103; https://doi.org/10.3390/rs17061103 - 20 Mar 2025

Viewed by 249

Abstract

In the field of weather forecasting, improving the accuracy of nowcasting is a highly researched topic, and radar echo extrapolation technology plays a crucial role in this process. Aiming to address the limitations of existing deep learning methods in radar echo extrapolation, this [...] Read more.

In the field of weather forecasting, improving the accuracy of nowcasting is a highly researched topic, and radar echo extrapolation technology plays a crucial role in this process. Aiming to address the limitations of existing deep learning methods in radar echo extrapolation, this paper proposes a spatio-temporal long short-term memory (LSTM) network model that integrates an attention mechanism and the full-dimensional dynamic convolution technique. The multi-scale spatial and temporal features of radar images can be fully extracted by an efficient multi-scale attention module to enhance the model’s ability to perceive global and local information. The full-dimensional dynamic convolutional module introduces the dynamic attention mechanism in the spatial position and input and output channels of the convolutional kernel, adaptively adjusts the weight of the convolutional kernel, and improves the flexibility and efficiency of feature extraction. Combined with the network constructed by the above modules, the accuracy and time dependence of the model for predicting the strong echo region are significantly improved. Our experiments based on Jiangsu meteorological radar data show that the model achieved excellent results in terms of the Critical Success Index (CSI) and Heidke Skill Score (HSS), which show its efficiency and stability in predicting radar echo, especially under the condition of a high 35 dBZ threshold, and its prediction performance improved significantly. It provides an effective solution for fine short-term impending precipitation forecasting. Full article

(This article belongs to the Special Issue Artificial Intelligence-Based Sensor Data Processing for Remote Sensing)

► Show Figures

Figure 1

22 pages, 2173 KiB

Open AccessArticle

The Intercity Industrial Distribution Effects of China’s High-Speed Railway: Evidence from Nighttime Light Remote Sensing Data

by Fangqu Niu and Lijia Zhu

Remote Sens. 2025, 17(6), 1102; https://doi.org/10.3390/rs17061102 - 20 Mar 2025

Viewed by 197

Abstract

High-speed railway (HSR) has become a key infrastructure that shapes land use, specifically industrial distribution, and therefore affects urban industrial structure and regional economic patterns. This paper develops a new approach to examine the intercity industrial distribution effects (IDE) of HSR using nighttime [...] Read more.

High-speed railway (HSR) has become a key infrastructure that shapes land use, specifically industrial distribution, and therefore affects urban industrial structure and regional economic patterns. This paper develops a new approach to examine the intercity industrial distribution effects (IDE) of HSR using nighttime light (NTL) data from 290 cities in China over a long period of time. Our study shows that the tertiary industries exhibit higher luminous intensity than the secondary industries, and the operation of HSR fosters the concentration of tertiary industries in megacities and supercities, especially those in the eastern economic regions, while leading to the dispersion of secondary industries from those cities. As a result, the proportion of tertiary industry in most medium and small cities decreased, and that of the secondary industry increased. Furthermore, among tertiary industries, producer services, especially transportation, warehousing, postal services, financial services, and leasing and business services, are most affected by HSR. These results highlight the intercity variation in the industrial impacts of HSR and provide valuable insights for industrial planning and policy-making in HSR cities. The proposed approach in this study can effectively identify the IDEs of HSR. Our findings suggest that cities cannot blindly rely on the operation of HSR to pursue economic development, and policymakers need to consider both the industrial situation of the HSR city itself and that of the cities connected through HSR to formulate distinct land use policies to address the impact of HSR on its industries. Full article

(This article belongs to the Special Issue Nighttime Light Remote Sensing Products for Urban Applications)

► Show Figures

Figure 1

18 pages, 5757 KiB

Open AccessArticle

Detection-Oriented Evaluation of SAR Dexterous Barrage Jamming Effectiveness

by Hai Zhu, Sinong Quan, Shiqi Xing, Haoyu Zhang and Yun Ren

Remote Sens. 2025, 17(6), 1101; https://doi.org/10.3390/rs17061101 - 20 Mar 2025

Viewed by 230

Abstract

The assessment of the jamming effect of Synthetic Aperture Radar (SAR) is the primary means to measure the reliability of the jamming, which can provide important guidance for the use of jamming strategies and patterns. This paper proposes a detection-oriented evaluation of the [...] Read more.

The assessment of the jamming effect of Synthetic Aperture Radar (SAR) is the primary means to measure the reliability of the jamming, which can provide important guidance for the use of jamming strategies and patterns. This paper proposes a detection-oriented evaluation of the effect of SAR dexterous barrage jamming. Starting from the detection, it divides the evaluation process into two stages: (1) for the case in which the target can be detected under the jamming scenario, two feature parameters, namely, the target exposion area and target relative magnitude, are extracted; (2) for the case in which the target cannot be detected under the jamming scenario, another three feature parameters, namely, jamming relative magnitude, average edge brightness, and local information entropy, are extracted. On this basis, two hierarchical evaluation candidates, the target exposure degree and jamming concealment degree, respectively, are designed, and a comprehensive evaluation index of the dexterous suppression degree is finally proposed. Jamming experiments are carried out from real and simulated SAR data with different scenarios, and the results demonstrate that the proposed method effectively measures the barrage jamming effects of different jamming-to-signal ratios and patterns. More importantly, it quantifies the relationship between suppression degree and detection rate, wherein the detection rate decreases by about 35% to 45% for every 0.1 increase in the suppression degree. Full article

(This article belongs to the Special Issue SAR Image Object Detection and Information Extraction: Methods and Applications)

► Show Figures

Figure 1

17 pages, 17812 KiB

Open AccessArticle

Multi-Instrument Analysis of Ionospheric Equatorial Plasma Bubbles over the Indian and Southeast Asian Longitudes During the 19–20 April 2024 Geomagnetic Storm

by Sampad Kumar Panda, Siva Sai Kumar Rajana, Chiranjeevi G. Vivek, Jyothi Ravi Kiran Kumar Dabbakuti, Wangshimenla Jamir and Punyawi Jamjareegulgarn

Remote Sens. 2025, 17(6), 1100; https://doi.org/10.3390/rs17061100 - 20 Mar 2025

Viewed by 869

Abstract

In this study, we explored the occurrence of near-sunrise equatorial plasma bubbles (EPBs) and inhibition of dusk-time EPBs during the geomagnetic storm (SYM-Hmin= −139 nT) of 19–20 April 2024 using multi-instrument observations over the Indian and Southeast Asian longitude sectors. The initial phase [...] Read more.

In this study, we explored the occurrence of near-sunrise equatorial plasma bubbles (EPBs) and inhibition of dusk-time EPBs during the geomagnetic storm (SYM-Hmin= −139 nT) of 19–20 April 2024 using multi-instrument observations over the Indian and Southeast Asian longitude sectors. The initial phase of this storm commenced around 0530 UT on 19 April 2024 and did not manifest any visible alterations in the ionospheric electric fields during the main phase of the storm, which corresponded to a period between post-sunset to midnight over the study region. However, during the recovery phase of the storm, the IMF Bz suddenly flipped northward and was associated with an overshielding of the penetrating electric fields, which triggered the formation of near-sunrise EPBs. Interestingly, the persistence of EPBs was also noticed for more than three hours after the sunrise terminator. Initially, sunrise EPBs were developed in the Southeast Asian region and later drifted toward the Indian longitude region, along with the sunrise terminator. Moreover, this study suggested that the occurrence of EPBs was suppressed due to the altered storm time electric fields at the dip equatorial region across the 70–90°E longitude sector in the recovery period. This study highlighted that even moderate geomagnetic storms can generate near-sunrise EPBs in a broader longitude sector due to penetrating electric fields in overshielding conditions, which can significantly affect trans-ionospheric signals. Full article

(This article belongs to the Special Issue Advances in GNSS Remote Sensing for Ionosphere Observation)

► Show Figures

Figure 1

23 pages, 7822 KiB

Open AccessArticle

Crowdsourcing User-Enhanced PPP-RTK with Weighted Ionospheric Modeling

by Qing Zhao, Shuguo Pan, Wang Gao, Xianlu Tao, Hao Liu and Zeyu Zhang

Remote Sens. 2025, 17(6), 1099; https://doi.org/10.3390/rs17061099 - 20 Mar 2025

Viewed by 239

Abstract

In the conventional PPP-RTK mode, the platform and users act only as the generator and the utilizer of ionospheric corrections, respectively. In sparse reference station networks or regions with an active ionosphere, high-precision modeling still faces challenges. This study utilizes the concept of [...] Read more.

In the conventional PPP-RTK mode, the platform and users act only as the generator and the utilizer of ionospheric corrections, respectively. In sparse reference station networks or regions with an active ionosphere, high-precision modeling still faces challenges. This study utilizes the concept of crowdsourcing and treats users as dynamic reference stations. By continuously feeding back ionospheric information to the platform, high-spatial-resolution modeling is achieved. Additionally, weight factors related to user positions are incorporated into conventional polynomial models to transform the regional ionosphere model from a common model into customized models, thereby providing more personalized services for different users. Validation was conducted with a sparse reference network with an average inter-station distance of approximately 391 km. While increasing the number of crowdsourcing users generally improves modeling performance, the enhancement also depends on their spatial distribution; that is, crowdsourcing users primarily provide localized improvements in their vicinity. Therefore, crowdsourcing users should ideally be uniformly distributed across the whole network. Compared with the conventional common model, the proposed customized model can more effectively characterize the irregular physical characteristics of the ionosphere, and the modeling accuracy is improved by about 12% to 41% in different scenarios. Furthermore, the performance of single-frequency PPP-RTK was verified on the terminal. In general, both crowdsourcing enhancement and the customized model can accelerate the convergence speed of the float solutions and improve positioning accuracy to varying degrees, and the epoch fix rate of the fixed solutions is also significantly improved. Full article

(This article belongs to the Special Issue GNSS Advanced Positioning Algorithms and Innovative Applications (2nd Edition))

► Show Figures

Figure 1

38 pages, 1656 KiB

Open AccessArticle

Amplitude and Phase Calibration with the Aid of Beacons in Microwave Imaging Radiometry by Aperture Synthesis: Algebraic Aspects and Algorithmic Implications

by Eric Anterrieu

Remote Sens. 2025, 17(6), 1098; https://doi.org/10.3390/rs17061098 - 20 Mar 2025

Viewed by 267

Abstract

In remote sensing via aperture synthesis, the complex gains of every elementary antenna have to be very well known for measuring accurate complex visibilities. The role of calibration is to estimate the instrumental and environmental variations that may affect interferometric measurements. This contribution [...] Read more.

In remote sensing via aperture synthesis, the complex gains of every elementary antenna have to be very well known for measuring accurate complex visibilities. The role of calibration is to estimate the instrumental and environmental variations that may affect interferometric measurements. This contribution focuses on the calibration of the effective transfer function of aperture synthesis radiometers with the aid of a radio beacon, in the same way radio-astronomers use quasi-stellar radio sources to calibrate that of radio-telescope arrays. If the amplitude calibration of complex gains does not raise any issue, it is shown that phase calibration may bring up serious challenges if it is not given special attention. Indeed, the phase of the complex visibilities cannot be roughly unwrapped as the risk of a wrong estimation of the complex gains is real and proven. This problem is overcome with the aid of a non-linear optimization algorithm for iteratively and smoothly unwrapping these phases. The performances of both amplitude and phase calibration are then assessed by means of numerical simulations with emphasis on the sensitivity of the accuracy to the inversion method as well as to various errors. Full article

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

► Show Figures

Figure 1

18 pages, 2362 KiB

Open AccessArticle

Hyperspectral Target Detection Based on Masked Autoencoder Data Augmentation

by Zhixuan Zhuang, Jinhui Lan and Yiliang Zeng

Remote Sens. 2025, 17(6), 1097; https://doi.org/10.3390/rs17061097 - 20 Mar 2025

Viewed by 276

Abstract

Deep metric learning combines deep learning with metric learning to explore the deep spectral space and distinguish between the target and background. Current target detection methods typically fail to accurately distinguish local differences between the target and background, leading to insufficient suppression of [...] Read more.

Deep metric learning combines deep learning with metric learning to explore the deep spectral space and distinguish between the target and background. Current target detection methods typically fail to accurately distinguish local differences between the target and background, leading to insufficient suppression of the pixels surrounding the target and poor detection performance. To solve this issue, a hyperspectral target detection method based on masked autoencoder data augmentation (HTD-DA) was proposed. HTD-DA includes a multi-scale spectral metric network based on a triplet network, which enhances the ability to learn local and global spectral variations using multi-scale feature extraction and feature fusion, thereby improving background suppression. To alleviate the lack of training data, a masked spectral data augmentation network was employed. It utilizes the entire hyperspectral image (HSI) training the network to learn spectral variability through mask-based reconstruction techniques and generate target samples based on the prior spectrum. Additionally, in search of more optimal spectral space, an Inter-class Difference Amplification Triplet (IDAT) Loss was introduced to enhance the separation between the target and background when finding the spectral space, by making full use of background and prior information. The experimental results demonstrated that the proposed model provides superior detection results. Full article

(This article belongs to the Special Issue Image Processing from Aerial and Satellite Imagery)

► Show Figures

Graphical abstract

13 pages, 7714 KiB

Open AccessTechnical Note

Geodetic Observations and Seismogenic Structures of the 2025 Mw 7.0 Dingri Earthquake: The Largest Normal Faulting Event in the Southern Tibet Rift

by Qingyi Liu, Jun Hua, Yingfeng Zhang, Wenyu Gong, Jianfei Zang, Guohong Zhang and Hongyi Li

Remote Sens. 2025, 17(6), 1096; https://doi.org/10.3390/rs17061096 - 20 Mar 2025

Viewed by 531

Abstract

The Mw 7.0 Dingri earthquake, which occurred on 7 January 2025, occurred at the southern end of the Xainza-Dinggyê Fault Zone within the South Tibet Rift (STR) system, in the Dengmecuo graben. It is the largest normal-faulting event in the region recorded by [...] Read more.

The Mw 7.0 Dingri earthquake, which occurred on 7 January 2025, occurred at the southern end of the Xainza-Dinggyê Fault Zone within the South Tibet Rift (STR) system, in the Dengmecuo graben. It is the largest normal-faulting event in the region recorded by modern instruments. Using Sentinel-1A and Lutan SAR data combined with strong-motion records, we derived the coseismic surface deformation and slip distribution. InSAR interferograms and displacement vectors confirm a typical normal-faulting pattern. The slip model, based on an elastic half-space assumption, identifies the Dengmecuo Fault as the source fault, with an average strike of ~187° and a dip of ~55°. The rupture was concentrated within the upper 10 km, with a maximum slip of 4–5 m at ~5 km depth, extending to the surface with ~3 m vertical displacement. Partial rupture (≤2 m) in the southern segment (5–10 km depth) did not reach the surface, likely due to lacustrine deposits or possible post-seismic stress release. The rupture bottom intersects the fault plane of the South Tibet Detachment System (STDS), suggesting a restraining effect on coseismic rupture propagation. Considering stress transfer along the Main Himalayan Thrust (MHT), we propose that the 2025 Dingri earthquake is closely associated with stress transfer following the 2015 Gorkha earthquake in the lower Himalayas. Full article

(This article belongs to the Special Issue Advanced SAR/InSAR Techniques in Understanding and Monitoring Geohazards)

► Show Figures

Figure 1

23 pages, 21654 KiB

Open AccessArticle

FQDNet: A Fusion-Enhanced Quad-Head Network for RGB-Infrared Object Detection

by Fangzhou Meng, Aoping Hong, Hongying Tang and Guanjun Tong

Remote Sens. 2025, 17(6), 1095; https://doi.org/10.3390/rs17061095 - 20 Mar 2025

Viewed by 374

Abstract

RGB-IR object detection provides a promising solution for complex scenarios, such as remote sensing and low-light environments, by leveraging the complementary strengths of visible and infrared modalities. Despite significant advancements, two key challenges remain: (1) effectively integrating multi-modal features within lightweight frameworks to [...] Read more.

RGB-IR object detection provides a promising solution for complex scenarios, such as remote sensing and low-light environments, by leveraging the complementary strengths of visible and infrared modalities. Despite significant advancements, two key challenges remain: (1) effectively integrating multi-modal features within lightweight frameworks to enable real-time performance and (2) fully utilizing multi-scale features, which are crucial for detecting objects of varying sizes but are often underexploited, leading to suboptimal accuracy. To address these challenges, we propose FQDNet, a novel RGB-IR object detection network that integrates an optimized fusion strategy with a Quad-Head detection framework. To enhance multi-modal feature fusion, we introduce a Channel Swap SCDown Block (CSSB) for initial feature interaction and a lightweight Spatial Channel Attention Fusion Module (SCAFM) to further refine the integration of complementary RGB-IR features. To improve multi-scale feature utilization, we designed the Dynamic-Weight-based Quad-Head Detector (DWQH), which dynamically assigns weights to different scales, enabling adaptive fusion and enhancing multi-scale feature representation. This mechanism significantly improves detection performance, particularly for small objects. Furthermore, to ensure real-time applicability, we incorporate lightweight optimizations, including the Partial Cross-Stage Pyramid (PCSP) and SCDown modules, which reduce computational complexity while maintaining high detection accuracy. FQDNet was evaluated on three public RGB-IR datasets—M3FD, VEDAI, and LLVIP—achieving mAP@[0.5:0.95] gains of 4.4%, 3.5%, and 3.1% over the baseline, with only a 0.4 M increase in parameters and 5.5 GFLOPs overhead. Compared to state-of-the-art RGB-IR object detection algorithms, our method strikes a better balance between detection accuracy and computational efficiency while exhibiting strong robustness across diverse detection scenarios. Full article

(This article belongs to the Special Issue Advances in Deep Fusion of Multi-Source Remote Sensing Images)

► Show Figures

Figure 1

23 pages, 5159 KiB

Open AccessArticle

Modifying NISAR’s Cropland Area Algorithm to Map Cropland Extent Globally

by Kaylee G. Sharp, Jordan R. Bell, Hannah G. Pankratz, Lori A. Schultz, Ronan Lucey, Franz J. Meyer and Andrew L. Molthan

Remote Sens. 2025, 17(6), 1094; https://doi.org/10.3390/rs17061094 - 20 Mar 2025

Viewed by 292

Abstract

Synthetic aperture radar (SAR) is emerging as a valuable dataset for monitoring crops globally. Unlike optical remote sensing, SAR can provide earth observations regardless of solar illumination or atmospheric conditions. Several methods that utilize SAR to identify agriculture rely on computationally expensive algorithms, [...] Read more.

Synthetic aperture radar (SAR) is emerging as a valuable dataset for monitoring crops globally. Unlike optical remote sensing, SAR can provide earth observations regardless of solar illumination or atmospheric conditions. Several methods that utilize SAR to identify agriculture rely on computationally expensive algorithms, such as machine learning, that require extensive training datasets, complex data pre-processing, or specialized software. The coefficient of variation (CV) method has been successful in identifying agricultural activity using several SAR sensors and is the basis of the Cropland Area algorithm for the upcoming NASA-Indian Space Research Organization (ISRO) SAR mission. The CV method derives a unique threshold for an AOI by optimizing Youden’s J-Statistic, where pixels above the threshold are classified as crop and pixels below are classified as non-crop, producing a binary crop/non-crop classification. Training this optimization process requires at least some existing cropland classification as an external reference dataset. In this paper, general CV thresholds are derived that can discriminate active agriculture (i.e., fields in use) from other land cover types without requiring a cropland reference dataset. We demonstrate the validity of our approach for three crop types: corn/soybean, wheat, and rice. Using data from the European Space Agency’s (ESA) Sentinel-1, a C-band SAR instrument, nine global AOIs, three for each crop type, were evaluated. Optimal thresholds were calculated and averaged for two AOIs per crop type for 2018–2022, resulting in 0.53, 0.31, and 0.26 thresholds for corn/soybean, wheat, and rice regions, respectively. The crop type average thresholds were then applied to an additional AOI of the same crop type, where they achieved 92%, 84%, and 83% accuracy for corn/soybean, wheat, and rice, respectively, when compared to ESA’s 2021 land cover product, WorldCover. The results of this study indicate that the use of the CV, along with the average crop type thresholds presented, is a fast, simple, and reliable technique to detect active agriculture in areas where either corn/soybean, wheat, or rice is the dominant crop type and where outdated or no reference datasets exist. Full article

(This article belongs to the Special Issue NISAR Global Observations for Ecosystem Science and Applications)

► Show Figures

Figure 1

13 pages, 10327 KiB

Open AccessArticle

Extraction Method for Factory Aquaculture Based on Multiscale Residual Attention Network

by Haiwei Zhang, Jialan Chu, Guize Liu, Yanlong Chen and Kaifei He

Remote Sens. 2025, 17(6), 1093; https://doi.org/10.3390/rs17061093 - 20 Mar 2025

Viewed by 212

Abstract

The rapid development of factory aquaculture not only brings economic benefits to coastal areas but also poses numerous ecological and environmental challenges. Therefore, understanding the distribution of coastal factory aquaculture is of great significance for ecological protection. To tackle the issue of the [...] Read more.

The rapid development of factory aquaculture not only brings economic benefits to coastal areas but also poses numerous ecological and environmental challenges. Therefore, understanding the distribution of coastal factory aquaculture is of great significance for ecological protection. To tackle the issue of the complex spectral and spatial characteristics in remote-sensing images of different factory aquaculture plants in coastal areas, a multiscale residual attention network (MRAN) model for extracting factory aquaculture information is proposed in this study. MRAN is a modification of the U-Net model. By introducing a residual structure, an attention module, and a multiscale connection MRAN can solve the problem of inadequately detailed information extraction from a complex background. In addition, the coastal areas of Huludao City and Dalian City in Liaoning Province were selected as the research areas, and experiments were conducted using the domestic Gaofen-1 remote-sensing image data. The results indicate that the pixel accuracy (PA), mean PA, and mean intersection over union of the proposed model are 98.31%, 97.85%, and 92.46%, respectively, which are superior to those of other comparison models. Moreover, the proposed model can effectively reduce misidentification and missing identification phenomena caused by complex backgrounds and multiple scales. Full article

(This article belongs to the Special Issue Ecological Environment Remote Sensing and Sustainable Development Evaluation in Coastal Zones)

► Show Figures

Figure 1

24 pages, 20151 KiB

Open AccessArticle

Digital Elevation Model-Driven River Channel Boundary Monitoring Using the Natural Breaks (Jenks) Method

by Rongjie Gui, Wenlong Song, Juan Lv, Yizhu Lu, Hongjie Liu, Tianshi Feng and Shaobo Linghu

Remote Sens. 2025, 17(6), 1092; https://doi.org/10.3390/rs17061092 - 20 Mar 2025

Viewed by 281

Abstract

River channels are fundamental geomorphological and hydrological features that play a critical role in regulating the Earth’s water cycle and ecosystems and influencing human activities. This study utilized Digital Elevation Model (DEM) data and multi-source remote sensing imagery (including GF-1 WFV, Sentinel-1, and [...] Read more.

River channels are fundamental geomorphological and hydrological features that play a critical role in regulating the Earth’s water cycle and ecosystems and influencing human activities. This study utilized Digital Elevation Model (DEM) data and multi-source remote sensing imagery (including GF-1 WFV, Sentinel-1, and Sentinel-2) to determine river channel dimensions. River water masks were obtained from multiple remote sensing imagery sources and processed through triangulation and segmentation to generate river reach results. Based on these segmented river reaches, buffer analysis was conducted. The buffer analysis results were then used to refine and clip the 5 m DEM and 12.5 m DEM datasets. Finally, river channels were extracted from the clipped DEM data using the natural breaks classification method. The classification accuracy was assessed using a confusion matrix. Experimental results demonstrate a high overall classification accuracy, reaching or exceeding 0.985, with classification consistency (Kappa coefficient) ranging from 0.78 to 0.81. The 5 m resolution DEM exhibited superior performance compared to the 12.5 m resolution DEM in river channel extraction, especially regarding the classification consistency (Kappa coefficient), with the 5 m resolution model outperforming the latter. This approach effectively delineates the river channel boundaries, transcends the constraints of a singular data source, enhances the precision and resilience of river extraction, and possesses several practical applications. The extracted data can support analyses of river evolution, facilitate hydrological modeling at the basin scale, improve flood disaster monitoring, and contribute to various other research domains. Full article

► Show Figures

Graphical abstract

18 pages, 7995 KiB

Open AccessArticle

INS/LiDAR Relative Navigation Design Based on Point Cloud Covariance Characteristics for Spacecraft Proximity Operation

by Dongyeon Park, Hyeongseob Shin and Sangkyung Sung

Remote Sens. 2025, 17(6), 1091; https://doi.org/10.3390/rs17061091 - 20 Mar 2025

Viewed by 241

Abstract

This paper proposes a pose estimation algorithm using INS and LiDAR for precise cooperative relative navigation between target and chaser spacecraft in a close docking mission scenario. Previous cooperative algorithms have proposed estimating position and pose transformations using typical matching methods or to [...] Read more.

This paper proposes a pose estimation algorithm using INS and LiDAR for precise cooperative relative navigation between target and chaser spacecraft in a close docking mission scenario. Previous cooperative algorithms have proposed estimating position and pose transformations using typical matching methods or to pre-extract and utilize features from point cloud data. However, in the case of general proximity rendezvous docking, a straight-line approach scenario with very few changes in attitude is usually assumed, and, in this case, pose estimation using simple matching techniques or feature point extraction leads to inaccurate results. To solve this problem, this paper performed a principal component analysis (PCA) based on ICP to align the initial transformation matrix. To keep the distribution of point cloud data constant, the point cloud at the time of docking was applied to ICP to minimize the change in the distribution of point clouds over time. Finally, we designed an EKF filter that estimates the relative position, velocity, and attitude using the INS model and combines it with the relative pose estimated from the point cloud; the proposed method showed the results of estimating the relative pose more effectively than the previous method. The simulation and experiment showed more accurate estimation results than the ICP method in position and attitude, respectively. In particular, in the case of position, both the simulation and experiment showed 0.46 m and 0.32 m better estimation results in the z-axis. Also, attitude estimation showed 0.11° and 2.66° better results in roll and 0.01° and 0.34° better results in pitch. This shows that the proposed algorithm provided better pose estimation results in the docking scenario in a straight line. Full article

► Show Figures

Figure 1

23 pages, 10335 KiB

Open AccessArticle

Multitemporal Spatial Analysis for Monitoring and Classification of Coal Mining and Reclamation Using Satellite Imagery

by Koni D. Prasetya and Fuan Tsai

Remote Sens. 2025, 17(6), 1090; https://doi.org/10.3390/rs17061090 - 20 Mar 2025

Viewed by 734

Abstract

Observing coal mining and reclamation activities using remote sensing avoids the need for physical site visits, which is important for environmental and land management. This study utilizes deep learning techniques with a U-Net and ResNet architecture to analyze Sentinel imagery in order to [...] Read more.

Observing coal mining and reclamation activities using remote sensing avoids the need for physical site visits, which is important for environmental and land management. This study utilizes deep learning techniques with a U-Net and ResNet architecture to analyze Sentinel imagery in order to track changes in coal mining and reclamation over time in Tapin Regency, Kalimantan, Indonesia. After gathering Sentinel 1 and 2 satellite imagery of Kalimantan Island, manually label coal mining areas are used to train a deep learning model. These labelled areas included open cuts, tailings dams, waste rock dumps, and water ponds associated with coal mining. Applying the deep learning model to multitemporal Sentinel 1 and 2 imagery allowed us to track the annual changes in coal mining areas from 2016 to 2021, while identifying reclamation sites where former coal mines had been restored to non-coal-mining use. An accuracy assessment resulted in an overall accuracy of 97.4%, with a Kappa value of 0.91, through a confusion matrix analysis. The results indicate that the reclamation effort increased more than twice in 2020 compared with previous years’ reclamation. This phenomenon was mainly affected by the massive increase in coal mining areas by over 40% in 2019. The proposed method provides a practical solution for detecting and monitoring open-pit coal mines while leveraging freely available data for consistent long-term observation. The primary limitation of this approach lies in the use of medium-resolution satellite imagery, which may result in lower precision compared to direct field measurements; however, the ability to integrate historical data with consistent temporal coverage makes it a viable alternative for large-scale and long-term monitoring. Full article

► Show Figures

Graphical abstract

34 pages, 32810 KiB

Open AccessArticle

Projecting Future Wetland Dynamics Under Climate Change and Land Use Pressure: A Machine Learning Approach Using Remote Sensing and Markov Chain Modeling

by Penghao Ji, Rong Su, Guodong Wu, Lei Xue, Zhijie Zhang, Haitao Fang, Runhong Gao, Wanchang Zhang and Donghui Zhang

Remote Sens. 2025, 17(6), 1089; https://doi.org/10.3390/rs17061089 - 20 Mar 2025

Cited by 2 | Viewed by 441

Abstract

Wetlands in the Yellow River Watershed of Inner Mongolia face significant reductions under future climate and land use scenarios, threatening vital ecosystem services and water security. This study employs high-resolution projections from NASA’s Global Daily Downscaled Projections (GDDP) and the Intergovernmental Panel on [...] Read more.

Wetlands in the Yellow River Watershed of Inner Mongolia face significant reductions under future climate and land use scenarios, threatening vital ecosystem services and water security. This study employs high-resolution projections from NASA’s Global Daily Downscaled Projections (GDDP) and the Intergovernmental Panel on Climate Change Sixth Assessment Report (IPCC AR6), combined with a machine learning and Cellular Automata–Markov (CA–Markov) framework to forecast the land cover transitions to 2040. Statistically downscaled temperature and precipitation data for two Shared Socioeconomic Pathways (SSP2-4.5 and SSP5-8.5) are integrated with satellite-based land cover (Landsat, Sentinel-1) from 2007 and 2023, achieving a high classification accuracy (over 85% overall, Kappa > 0.8). A Maximum Entropy (MaxEnt) analysis indicates that rising temperatures, increased precipitation variability, and urban–agricultural expansion will exacerbate hydrological stress, driving substantial wetland contraction. Although certain areas may retain or slightly expand their wetlands, the dominant trend underscores the urgency of spatially targeted conservation. By synthesizing downscaled climate data, multi-temporal land cover transitions, and ecological modeling, this study provides high-resolution insights for adaptive water resource planning and wetland management in ecologically sensitive regions. Full article

(This article belongs to the Special Issue Application of Remote Sensing Technology in Wetland Ecology)

► Show Figures

Figure 1

30 pages, 31329 KiB

Open AccessArticle

Virtual 3D Multi-Angle Modeling and Analysis of Nighttime Lighting in Complex Urban Scenes

by Xueqian Gao, Yuehan Wang, Fan Yang, Ximin Cui, Xuesheng Zhao, Mengjun Chao, Xiaoling Wei, Jinke Liu, Guobin Shi, Hansi Yao, Qingqing Li and Wei Guo

Remote Sens. 2025, 17(6), 1088; https://doi.org/10.3390/rs17061088 - 20 Mar 2025

Viewed by 272

Abstract

Urban nighttime lighting extends human activity hours and enhances safety but also wastes energy and causes light pollution. Influenced by building obstructions and surface reflections, light emissions exhibit significant anisotropy. Remote sensing can be used to observe nighttime lighting from high altitudes, but [...] Read more.

Urban nighttime lighting extends human activity hours and enhances safety but also wastes energy and causes light pollution. Influenced by building obstructions and surface reflections, light emissions exhibit significant anisotropy. Remote sensing can be used to observe nighttime lighting from high altitudes, but ground lighting anisotropy introduces angle-related errors. This study constructed a 3D urban nighttime lighting model using virtual simulations and conducted multi-angle observations to investigate anisotropy and its influencing factors. The results show that the illuminance distribution in urban functional areas is typically uneven, with ground-level illuminance varying linearly or exponentially with zenith angle and quadratically with azimuth angle. Some areas exhibit uniform illuminance without significant anisotropy. Nighttime light anisotropy is closely linked to urban geometry and light distribution, with building height, layout, and light source arrangement significantly influencing the anisotropic characteristics. The findings enhance our understanding of nighttime light anisotropy, provide a basis for developing angular effect models of complex scenarios, and quantify the upward light emission angles and intensities. These insights can be used to support corrections for multi-angle spaceborne nighttime lighting observations, contributing to more accurate data for urban planning and light pollution mitigation. Full article

(This article belongs to the Special Issue Remote Sensing Technologies, Applications and Perspectives at Night: Nightlight, Nighttime Thermal Infrared and Synthetic Aperture Radar (SAR))

► Show Figures

Figure 1

22 pages, 3976 KiB

Open AccessArticle

Spatial Distribution of Urban Anthropogenic Carbon Emissions Revealed from the OCO-3 Snapshot XCO₂ Observations: A Case Study of Shanghai

by Mengwei Jia, Yingsong Li, Fei Jiang, Shuzhuang Feng, Hengmao Wang, Jun Wang, Mousong Wu and Weimin Ju

Remote Sens. 2025, 17(6), 1087; https://doi.org/10.3390/rs17061087 - 20 Mar 2025

Viewed by 394

Abstract

The accurate quantification of anthropogenic carbon dioxide (CO₂) emissions in urban areas is hindered by high uncertainties in emission inventories. We assessed the spatial distributions of three anthropogenic CO₂ emission inventories in Shanghai, China—MEIC (0.25° × 0.25°), ODIAC (1 km [...] Read more.

The accurate quantification of anthropogenic carbon dioxide (CO₂) emissions in urban areas is hindered by high uncertainties in emission inventories. We assessed the spatial distributions of three anthropogenic CO₂ emission inventories in Shanghai, China—MEIC (0.25° × 0.25°), ODIAC (1 km × 1 km), and a local inventory (LOCAL) (4 km × 4 km)—and compared simulated CO₂ column concentrations (XCO₂) from WRF-CMAQ against OCO-3 satellite Snapshot Mode XCO₂ observations. Emissions differ by up to a factor of 2.6 among the inventories. ODIAC shows the highest emissions, particularly in densely populated areas, reaching 4.6 and 8.5 times for MEIC and LOCAL in the central area, respectively. Emission hotspots of ODIAC and MEIC are the city center, while those of LOCAL are point sources. Overall, by comparing the simulated XCO₂ values driven by three emission inventories and the WRF-CMAQ model with OCO-3 satellite XCO₂ observations, LOCAL demonstrates the highest accuracy with slight underestimation, whereas ODIAC overestimates the most. Regionally, ODIAC performs better in densely populated areas but overestimates by around 0.22 kt/d/km² in relatively sparsely populated districts. LOCAL underestimates by 0.39 kt/d/km² in the center area but is relatively accurate near point sources. Moreover, MEIC’s coarse resolution causes substantial regional errors. These findings provide critical insights into spatial variability and precision errors in emission inventories, which are essential for improving urban carbon inversion. Full article

► Show Figures

Figure 1

19 pages, 3423 KiB

Open AccessArticle

Integrating Genetic Algorithm and Geographically Weighted Approaches into Machine Learning Improves Soil pH Prediction in China

by Wantao Zhang, Jingyi Ji, Binbin Li, Xiao Deng and Mingxiang Xu

Remote Sens. 2025, 17(6), 1086; https://doi.org/10.3390/rs17061086 - 20 Mar 2025

Viewed by 285

Abstract

Accurate soil pH prediction is critical for soil management and ecological environmental protection. Machine learning (ML) models have been widely applied in the field of soil pH prediction. However, when using these models, the spatial heterogeneity of the relationship between soil and environmental [...] Read more.

Accurate soil pH prediction is critical for soil management and ecological environmental protection. Machine learning (ML) models have been widely applied in the field of soil pH prediction. However, when using these models, the spatial heterogeneity of the relationship between soil and environmental variables is often not fully considered, which limits the predictive capability of the models, especially in large-scale regions with complex soil landscapes. To address these challenges, this study collected soil pH data from 4335 soil surface points (0–20 cm) obtained from the China Soil System Survey, combined with a multi-source environmental covariate. This study integrates Geographic Weighted Regression (GWR) with three ML models (Random Forest, Cubist, and XGBoost) and designs and develops three geographically weighted machine learning models optimized by Genetic Algorithms to improve the prediction of soil pH values. Compared to GWR and traditional ML models, the R² of the geographic weighted random forest (GWRF), geographic weighted Cubist (GWCubist), and geographic weighted extreme gradient boosting (GWXGBoost) models increased by 1.98% to 14.29%, while the RMSE decreased by 1.81% to 11.98%. Among the three models, the GWRF model performed the best and effectively reduced uncertainty in soil pH mapping. Mean Annual Precipitation and the Normalized Difference Vegetation Index are two key environmental variables influencing the prediction of soil pH, and they have a significant negative impact on the spatial distribution of soil pH. These findings provide a scientific basis for effective soil health management and the implementation of large-scale soil modeling programs. Full article

► Show Figures

Figure 1

20 pages, 12209 KiB

Open AccessArticle

Evaluating the Performance of Irrigation Using Remote Sensing Data and the Budyko Hypothesis: A Case Study in Northwest China

by Dingwang Zhou, Chaolei Zheng, Li Jia, Massimo Menenti, Jing Lu and Qiting Chen

Remote Sens. 2025, 17(6), 1085; https://doi.org/10.3390/rs17061085 - 19 Mar 2025

Viewed by 247

Abstract

Evaluating the performance of irrigation water use is essential for efficient and sustainable water resource management. However, existing approaches often lack systematic quantification of irrigation water consumption and fail to differentiate between the use of precipitation and anthropogenic appropriation of water flows. Building [...] Read more.

Evaluating the performance of irrigation water use is essential for efficient and sustainable water resource management. However, existing approaches often lack systematic quantification of irrigation water consumption and fail to differentiate between the use of precipitation and anthropogenic appropriation of water flows. Building on the green–blue water concept, consumptive water use, assumed equal to actual evapotranspiration (ET_a), was partitioned into green ET (GET) and blue ET (BET) using remote sensing data and the Budyko hypothesis. A novel BET metric of consumptive irrigation water use was developed and applied to the irrigated lands in northwest China to evaluate the performance of irrigation from 2001 to 2021. The results showed that in terms of total available water resources (precipitation + gross irrigation water (GIW)) compared to irrigation water demand, estimated as reference evapotranspiration (ET₀), Ningxia has sufficient water supply to meet irrigation demand, while the Hexi Corridor faces increasing risks of unsustainable water use. The Hetao irrigation scheme has shifted from a fragile supply–demand balance to a situation where water demand far exceeds availability. In Xinjiang, the balance between water supply and demand is tight. Furthermore, when considering the available water (GIW) relative to the net irrigation water demand (ET₀-GET), the Hexi Corridor faces significant water deficits, and Ningxia and Xinjiang are close to meeting local irrigation water demands by relying on current water availability and efficient irrigation practices. It is noteworthy that the BET remains lower than the GIW in northwest China (excluding the Hexi Corridor in recent years). The ratio of the BET to GIW is an estimate of the scheme irrigation efficiency, which was equal to 0.54 for all irrigation schemes taken together. In addition, the irrigation water use efficiency, estimated as the ratio of BET to net irrigation water, was evaluated in detail, and it was found that in the last 10 years the irrigation water use efficiency improved in Ningxia, the Hetao irrigation scheme, and Xinjiang. However, the Hexi Corridor continues to face severe net irrigation water deficits, suggesting the likelihood of groundwater use to sustain irrigated agriculture. BET innovatively separates consumptive use of precipitation (green water) and consumptive use of irrigation (blue water), a critical advancement beyond conventional approaches’ estimates that merge these distinct hydrological components to help quantifying water use efficiency. Full article

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

► Show Figures

Graphical abstract

22 pages, 12104 KiB

Open AccessArticle

Dual-Branch Diffusion Detection Model for Photovoltaic Array and Hotspot Defect Detection in Infrared Images

by Ruide Li, Wenjun Yan and Chaoqun Xia

Remote Sens. 2025, 17(6), 1084; https://doi.org/10.3390/rs17061084 - 19 Mar 2025

Viewed by 259

Abstract

Failures in solar photovoltaic (PV) modules generate heat, leading to various hotspots observable in infrared images. Automated hotspot detection technology enables rapid fault identification in PV systems, while PV array detection, leveraging geometric cues from infrared images, facilitates the precise localization of defects. [...] Read more.

Failures in solar photovoltaic (PV) modules generate heat, leading to various hotspots observable in infrared images. Automated hotspot detection technology enables rapid fault identification in PV systems, while PV array detection, leveraging geometric cues from infrared images, facilitates the precise localization of defects. This study tackles the complexities of detecting PV array regions and diverse hotspot defects in infrared imaging, particularly under the conditions of complex backgrounds, varied rotation angles, and the small scale of defects. The proposed model encodes infrared images to extract semantic features, which are then processed through an PV array detection branch and a hotspot detection branch. The array branch employs a diffusion-based anchor-free mechanism with rotated bounding box regression, enabling the robust detection of arrays with diverse rotational angles and irregular layouts. The defect branch incorporates a novel inside-awareness loss function designed to enhance the detection of small-scale objects. By explicitly modeling the dependency distribution between arrays and defects, this loss function effectively reduces false positives in hotspot detection. Experimental validation on a comprehensive PV dataset demonstrates the superiority of the proposed method, achieving a mean average precision (mAP) of 71.64% for hotspot detection and 97.73% for PV array detection. Full article

(This article belongs to the Special Issue Intelligent Processing and Application of UAV Remote Sensing Image Data)

► Show Figures

Figure 1

24 pages, 5485 KiB

Open AccessArticle

A Machine Learning Algorithm Using Texture Features for Nighttime Cloud Detection from FY-3D MERSI L1 Imagery

by Yilin Li, Yuhao Wu, Jun Li, Anlai Sun, Naiqiang Zhang and Yonglou Liang

Remote Sens. 2025, 17(6), 1083; https://doi.org/10.3390/rs17061083 - 19 Mar 2025

Viewed by 282

Abstract

Accurate cloud detection is critical for quantitative applications of satellite-based advanced imager observations, yet nighttime cloud detection presents challenges due to the lack of visible and near-infrared spectral information. Nighttime cloud detection using infrared (IR)-only information needs to be improved. Based on a [...] Read more.

Accurate cloud detection is critical for quantitative applications of satellite-based advanced imager observations, yet nighttime cloud detection presents challenges due to the lack of visible and near-infrared spectral information. Nighttime cloud detection using infrared (IR)-only information needs to be improved. Based on a collocated dataset from Fengyun-3D Medium Resolution Spectral Imager (FY-3D MERSI) Level 1 data and CALIPSO CALIOP lidar Level 2 product, this study proposes a novel framework leveraging Light Gradient-Boosting Machine (LGBM), integrated with grey level co-occurrence matrix (GLCM) features extracted from IR bands, to enhance nighttime cloud detection capabilities. The LGBM model with GLCM features demonstrates significant improvements, achieving an overall accuracy (OA) exceeding 85% and an F1-Score (F1) of nearly 0.9 when validated with an independent CALIOP lidar Level 2 product. Compared to the threshold-based algorithm that has been used operationally, the proposed algorithm exhibits superior and more stable performance across varying solar zenith angles, surface types, and cloud altitudes. Notably, the method produced over 82% OA over the cryosphere surface. Furthermore, compared to LGBM models without GLCM inputs, the enhanced model effectively mitigates the thermal stripe effect of MERSI L1 data, yielding more accurate cloud masks. Further evaluation with collocated MODIS-Aqua cloud mask product indicates that the proposed algorithm delivers more precise cloud detection (OA: 90.30%, F1: 0.9397) compared to that of the MODIS product (OA: 84.66%, F1: 0.9006). This IR-alone algorithm advancement offers a reliable tool for nighttime cloud detection, significantly enhancing the quantitative applications of satellite imager observations. Full article

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

► Show Figures

Figure 1

29 pages, 19804 KiB

Open AccessArticle

Spatio-Temporal Influences of Urban Land Cover Changes on Thermal-Based Environmental Criticality and Its Prediction Using CA-ANN Model over Kolkata (India)

by Sayantani Bhattacharyya, Suman Sinha, Maya Kumari, Varun Narayan Mishra, Fahdah Falah Ben Hasher, Marta Szostak and Mohamed Zhran

Remote Sens. 2025, 17(6), 1082; https://doi.org/10.3390/rs17061082 - 19 Mar 2025

Viewed by 354

Abstract

Rapid urbanization and the consequent alteration in land use and land cover (LULC) significantly change the natural landscape and adversely affect hydrological cycles, biological systems, and various ecosystem services, especially in the developing world. Thus, it is vital to study the environmental conditions [...] Read more.

Rapid urbanization and the consequent alteration in land use and land cover (LULC) significantly change the natural landscape and adversely affect hydrological cycles, biological systems, and various ecosystem services, especially in the developing world. Thus, it is vital to study the environmental conditions of a region to mitigate the negative impacts of urbanization. Out of a wide array of parameters, the Environmental Criticality Index (ECI), a relatively new concept, was used in this study, which was conducted over the Kolkata Metropolitan Area (KMA). It was derived using Land Surface Temperature (LST) and Normalized Difference Vegetation Index (NDVI) to quantify heat-related impact. An increase in the percentage of land area under high ECI categories, from 23.93% in 2000 to 32.37% in 2020, indicated a progressive increase in criticality. The Spatio-temporal Thermal-based Environmental Criticality Consistency Index (STTECCI) and hotspot analysis identified the urban and industrial areas in KMA as criticality hotspots, consistently recording higher ECI. The correlation analysis between ECI and LULC features revealed that there exists a negative correlation between ECI and natural vegetation and agriculture, while built-up areas and ECI are positively correlated. Bare lands, despite being positively correlated with ECI, have an insignificant relationship with it. Also, the designed built-up index extracted the built-up areas with an accuracy of 89.5% (kappa = 0.78). The future scenario of ECI in KMA was predicted using Modules for Land Use Change Evaluation (MOLUSCE) with an accuracy level above 90%. The percentage of land area under low ECI categories is expected to decline from 50.02% in 2000 to 35.6% in 2040, while the percentage of land area under high ECI categories is expected to increase from 23.93% in 2000 to 36.56% in 2040. This study can contribute towards the development of tailored management strategies that foster sustainable growth, resilience, and alignment with the Sustainable Development Goals, ensuring a balance between economic development and environmental preservation. Full article

(This article belongs to the Special Issue New Advances in High-Resolution Remote Sensing Applied for Land Use/Land Cover and Forest Succession Monitoring)

► Show Figures

Figure 1

5 pages, 5378 KiB

Open AccessEditorial

Radar for Space Observation: Systems, Methods and Applications

by Vassilis Karamanavis

Remote Sens. 2025, 17(6), 1081; https://doi.org/10.3390/rs17061081 - 19 Mar 2025

Viewed by 226

Abstract

In today’s world, where near-Earth space constitutes an increasingly congested and contested theater of economic, political, and military activities for the growing number of space-faring nations, the significance of actionable situational awareness cannot be overstated [...] Full article

(This article belongs to the Special Issue Radar for Space Observation: Systems, Methods and Applications)

21 pages, 4753 KiB

Open AccessArticle

Evaluation of Scale Effects on UAV-Based Hyperspectral Imaging for Remote Sensing of Vegetation

by Tie Wang, Tingyu Guan, Feng Qiu, Leizhen Liu, Xiaokang Zhang, Hongda Zeng and Qian Zhang

Remote Sens. 2025, 17(6), 1080; https://doi.org/10.3390/rs17061080 - 19 Mar 2025

Viewed by 337

Abstract

With the rapid advancement of unmanned aerial vehicles (UAVs) in recent years, UAV-based remote sensing has emerged as a highly efficient and practical tool for environmental monitoring. In vegetation remote sensing, UAVs equipped with hyperspectral sensors can capture detailed spectral information, enabling precise [...] Read more.

With the rapid advancement of unmanned aerial vehicles (UAVs) in recent years, UAV-based remote sensing has emerged as a highly efficient and practical tool for environmental monitoring. In vegetation remote sensing, UAVs equipped with hyperspectral sensors can capture detailed spectral information, enabling precise monitoring of plant health and the retrieval of physiological and biochemical parameters. A critical aspect of UAV-based vegetation remote sensing is the accurate acquisition of canopy reflectance. However, due to the mobility of UAVs and the variation in flight altitude, the data are susceptible to scale effects, where changes in spatial resolution can significantly impact the canopy reflectance. This study investigates the spatial scale issue of UAV hyperspectral imaging, focusing on how varying flight altitudes influence atmospheric correction, vegetation viewer geometry, and canopy heterogeneity. Using hyperspectral images captured at different flight altitudes at a Chinese fir forest stand, we propose two atmospheric correction methods: one based on a uniform grey reference panel at the same altitude and another based on altitude-specific grey reference panels. The reflectance spectra and vegetation indices, including NDVI, EVI, PRI, and CIRE, were computed and analyzed across different altitudes. The results show significant variations in vegetation indices at lower altitudes, with NDVI and CIRE demonstrating the largest changes between 50 m and 100 m, due to the heterogeneous forest canopy structure and near-infrared scattering. For instance, NDVI increased by 18% from 50 m to 75 m and stabilized after 100 m, while the standard deviation decreased by 32% from 50 m to 250 m, indicating reduced heterogeneity effects. Similarly, PRI exhibited notable increases at lower altitudes, attributed to changes in viewer geometry, canopy shadowing and soil background proportions, stabilizing above 100 m. Above 100 m, the impact of canopy heterogeneity diminished, and variations in vegetation indices became minimal (<3%), although viewer geometry effects persisted. These findings emphasize that conducting UAV hyperspectral observations at altitudes above at least 100 m minimizes scale effects, ensuring more consistent and reliable data for vegetation monitoring. The study highlights the importance of standardized atmospheric correction protocols and optimal altitude selection to improve the accuracy and comparability of UAV-based hyperspectral data, contributing to advancements in vegetation remote sensing and carbon estimation. Full article

(This article belongs to the Section Forest Remote Sensing)

► Show Figures

Figure 1

17 pages, 2800 KiB

Open AccessTechnical Note

A Novel Method for PolISAR Interpretation of Space Target Structure Based on Component Decomposition and Coherent Feature Extraction

by Zhuo Chen, Zhiming Xu, Xiaofeng Ai, Qihua Wu, Xiaobin Liu and Jianghua Cheng

Remote Sens. 2025, 17(6), 1079; https://doi.org/10.3390/rs17061079 - 19 Mar 2025

Viewed by 217

Abstract

Inverse Synthetic Aperture Radar (ISAR) serves as a valuable instrument for surveillance of space targets. There has been a great deal of research on space target identification using ISAR. However, the polarization characteristics of space target components are rarely studied. Polarimetric Inverse Synthetic [...] Read more.

Inverse Synthetic Aperture Radar (ISAR) serves as a valuable instrument for surveillance of space targets. There has been a great deal of research on space target identification using ISAR. However, the polarization characteristics of space target components are rarely studied. Polarimetric Inverse Synthetic Aperture Radar (PolISAR) comprises two information dimensions, namely, polarization and image, enabling a more comprehensive understanding of target structures. This paper proposes a space target structure polarization interpretation method based on component decomposition and PolISAR feature extraction. The proposed method divides the target into components at the stage of modeling. Subsequently, electromagnetic calculations are performed for each component. The names of these components are used to label the dataset. Multiple polarization decomposition techniques are applied and many polarization features are obtained. The mapping correlations between the interpreted results and authentic target structures are improved through preferential selection of polarization features. Ultimately, the method is validated through analysis of simulation and anechoic chamber measurement data. The results show that the proposed method exhibits a more intuitive correlation with the authentic target structures compared to traditional polarized interpretation methods based on Cameron decomposition. Full article

(This article belongs to the Special Issue Technical Developments in Radar—Processing and Application (2nd Edition))

► Show Figures

Figure 1

29 pages, 23397 KiB

Open AccessArticle

Dual Attention Fusion Enhancement Network for Lightweight Remote-Sensing Image Super-Resolution

by Wangyou Chen, Shenming Qu, Laigan Luo and Yongyong Lu

Remote Sens. 2025, 17(6), 1078; https://doi.org/10.3390/rs17061078 - 19 Mar 2025

Viewed by 352

Abstract

In the field of remote sensing, super-resolution methods based on deep learning have made significant progress. However, redundant feature extraction and inefficient feature fusion can, respectively, result in excessive parameters and restrict the precise reconstruction of features, making the model difficult to deploy [...] Read more.

In the field of remote sensing, super-resolution methods based on deep learning have made significant progress. However, redundant feature extraction and inefficient feature fusion can, respectively, result in excessive parameters and restrict the precise reconstruction of features, making the model difficult to deploy in practical remote-sensing tasks. To address this issue, we propose a lightweight Dual Attention Fusion Enhancement Network (DAFEN) for remote-sensing image super-resolution. Firstly, we design a lightweight Channel-Spatial Lattice Block (CSLB), which consists of Group Residual Shuffle Blocks (GRSB) and a Channel-Spatial Attention Interaction Module (CSAIM). The GRSB improves the efficiency of redundant convolution operations, while the CSAIM enhances interactive learning. Secondly, to achieve superior feature fusion and enhancement, we design a Forward Fusion Enhancement Module (FFEM). Through the forward fusion strategy, more high-level feature details are retained for better adaptation to remote-sensing tasks. In addition, the fused features are further refined and rescaled by Self-Calibrated Group Convolution (SCGC) and Contrast-aware Channel Attention (CCA), respectively. Extensive experiments demonstrate that DAFEN achieves better or comparable performance compared with state-of-the-art lightweight super-resolution models while reducing complexity by approximately 10∼48%. Full article

(This article belongs to the Special Issue Recent Advances in Deep Learning-Based High-Resolution Image Processing and Analysis)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Remote Sens., Volume 17, Issue 6 (March-2 2025) – 164 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI