Remote Sensing

24 pages, 986 KiB

Open AccessArticle

DBSF-Net: Infrared Image Colorization Based on the Generative Adversarial Model with Dual-Branch Feature Extraction and Spatial-Frequency-Domain Discrimination

by Shaopeng Li, Decao Ma, Yao Ding, Yong Xian and Tao Zhang

Remote Sens. 2024, 16(20), 3766; https://doi.org/10.3390/rs16203766 - 10 Oct 2024

Abstract

Thermal infrared cameras can image stably in complex scenes such as night, rain, snow, and dense fog. Still, humans are more sensitive to visual colors, so there is an urgent need to convert infrared images into color images in areas such as assisted [...] Read more.

Thermal infrared cameras can image stably in complex scenes such as night, rain, snow, and dense fog. Still, humans are more sensitive to visual colors, so there is an urgent need to convert infrared images into color images in areas such as assisted driving. This paper studies a colorization method for infrared images based on a generative adversarial model. The proposed dual-branch feature extraction network ensures the stability of the content and structure of the generated visible light image; the proposed discrimination strategy combining spatial and frequency domain hybrid constraints effectively improves the problem of undersaturated coloring and the loss of texture details in the edge area of the generated visible light image. The comparative experiment of the public infrared visible light paired data set shows that the algorithm proposed in this paper has achieved the best performance in maintaining the consistency of the content structure of the generated image, restoring the image color distribution, and restoring the image texture details. Full article

(This article belongs to the Special Issue The Recent Progression of Machine Learning in Remote Sensing: Theory and Modelling)

23 pages, 32897 KiB

Open AccessArticle

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

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

30 pages, 716 KiB

Open AccessReview

Advancing Arctic Sea Ice Remote Sensing with AI and Deep Learning: Opportunities and Challenges

by Wenwen Li, Chia-Yu Hsu and Marco Tedesco

Remote Sens. 2024, 16(20), 3764; https://doi.org/10.3390/rs16203764 - 10 Oct 2024

Abstract

Revolutionary advances in artificial intelligence (AI) in the past decade have brought transformative innovation across science and engineering disciplines. In the field of Arctic science, we have witnessed an increasing trend in the adoption of AI, especially deep learning, to support the analysis [...] Read more.

Revolutionary advances in artificial intelligence (AI) in the past decade have brought transformative innovation across science and engineering disciplines. In the field of Arctic science, we have witnessed an increasing trend in the adoption of AI, especially deep learning, to support the analysis of Arctic big data and facilitate new discoveries. In this paper, we provide a comprehensive review of the applications of deep learning in sea ice remote sensing domains, focusing on problems such as sea ice lead detection, thickness estimation, sea ice concentration and extent forecasting, motion detection, and sea ice type classification. In addition to discussing these applications, we also summarize technological advances that provide customized deep learning solutions, including new loss functions and learning strategies to better understand sea ice dynamics. To promote the growth of this exciting interdisciplinary field, we further explore several research areas where the Arctic sea ice community can benefit from cutting-edge AI technology. These areas include improving multimodal deep learning capabilities, enhancing model accuracy in measuring prediction uncertainty, better leveraging AI foundation models, and deepening integration with physics-based models. We hope that this paper can serve as a cornerstone in the progress of Arctic sea ice research using AI and inspire further advances in this field. Full article

(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

27 pages, 13175 KiB

Open AccessArticle

Tree Completion Net: A Novel Vegetation Point Clouds Completion Model Based on Deep Learning

by Binfu Ge, Shengyi Chen, Weibing He, Xiaoyong Qiang, Jingmei Li, Geer Teng and Fang Huang

Remote Sens. 2024, 16(20), 3763; https://doi.org/10.3390/rs16203763 - 10 Oct 2024

Abstract

To improve the integrity of vegetation point clouds, the missing vegetation point can be compensated through vegetation point clouds completion technology. Further, it can enhance the accuracy of these point clouds’ applications, particularly in terms of quantitative calculations, such as for the urban [...] Read more.

To improve the integrity of vegetation point clouds, the missing vegetation point can be compensated through vegetation point clouds completion technology. Further, it can enhance the accuracy of these point clouds’ applications, particularly in terms of quantitative calculations, such as for the urban living vegetation volume (LVV). However, owing to factors like the mutual occlusion between ground objects, sensor perspective, and penetration ability limitations resulting in missing single tree point clouds’ structures, the existing completion techniques cannot be directly applied to the single tree point clouds’ completion. This study combines the cutting-edge deep learning techniques, for example, the self-supervised and multiscale Encoder (Decoder), to propose a tree completion net (TC-Net) model that is suitable for the single tree structure completion. Being motivated by the attenuation of electromagnetic waves through a uniform medium, this study proposes an uneven density loss pattern. This study uses the local similarity visualization method, which is different from ordinary Chamfer distance (CD) values and can better assist in visually assessing the effects of point cloud completion. Experimental results indicate that the TC-Net model, based on the uneven density loss pattern, effectively identifies and compensates for the missing structures of single tree point clouds in real scenarios, thus reducing the average CD value by above 2.0, with the best result dropping from 23.89 to 13.08. Meanwhile, experiments on a large-scale tree dataset show that TC-Net has the lowest average CD value of 13.28. In the urban LVV estimates, the completed point clouds have reduced the average MAE, RMSE, and MAPE from 9.57, 7.78, and 14.11% to 1.86, 2.84, and 5.23%, respectively, thus demonstrating the effectiveness of TC-Net. 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

20 pages, 8335 KiB

Open AccessArticle

Evaluating the Multidimensional Stability of Regional Ecosystems Using the LandTrendr Algorithm

by Lijuan Li, Jiaqiang Du, Jin Wu, Zhilu Sheng, Xiaoqian Zhu, Zebang Song, Guangqing Zhai and Fangfang Chong

Remote Sens. 2024, 16(20), 3762; https://doi.org/10.3390/rs16203762 - 10 Oct 2024

Abstract

Stability is a key characteristic for understanding ecosystem processes and evolution. However, research on the stability of complex ecosystems often faces limitations, such as reliance on single parameters and insufficient representation of continuous changes. This study developed a multidimensional stability assessment system for [...] Read more.

Stability is a key characteristic for understanding ecosystem processes and evolution. However, research on the stability of complex ecosystems often faces limitations, such as reliance on single parameters and insufficient representation of continuous changes. This study developed a multidimensional stability assessment system for regional ecosystems based on disturbances. Focusing on the lower reaches of the Yellow River Basin (LR-YRB), we integrated the remote sensing ecological index (RSEI) with texture structural parameters, and applied the Landsat-based detection of trends in disturbance and recovery (LandTrendr) algorithm to analyze the continuous changes in disturbances and recovery from 1986 to 2021, facilitating the quantification and evaluation of resistance, resilience, and temporal stability. The results showed that 72.27% of the pixels experienced 1–9 disturbances, indicating the region’s sensitivity to external factors. The maximum disturbances primarily lasted 2–3 years, with resistance and resilience displaying inverse spatial patterns. Over the 35-year period, 61.01% of the pixels exhibited moderate temporal stability. Approximately 59.83% of the pixels recovered or improved upon returning to pre-disturbance conditions after maximum disturbances, suggesting a strong recovery capability. The correlation among stability dimensions was low and influenced by disturbance intensity, underscoring the necessity for a multidimensional assessment of regional ecosystem stability based on satellite remote sensing. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Land Cover Changes and Associated Environmental Effects: Progress, Challenges, and Opportunities)

► Show Figures

Figure 1

24 pages, 7287 KiB

Open AccessArticle

Lightweight Design for Infrared Dim and Small Target Detection in Complex Environments

by Yan Chang, Decao Ma, Yao Ding, Kefu Chen and Daming Zhou

Remote Sens. 2024, 16(20), 3761; https://doi.org/10.3390/rs16203761 - 10 Oct 2024

Abstract

In the intricate and dynamic infrared imaging environment, the detection of infrared dim and small targets becomes notably challenging due to their feeble radiation intensity, intricate background noise, and high interference characteristics. To tackle this issue, this paper introduces a lightweight detection and [...] Read more.

In the intricate and dynamic infrared imaging environment, the detection of infrared dim and small targets becomes notably challenging due to their feeble radiation intensity, intricate background noise, and high interference characteristics. To tackle this issue, this paper introduces a lightweight detection and recognition algorithm, named YOLOv5-IR, and further presents an even more lightweight version, YOLOv5-IRL. Firstly, a lightweight network structure incorporating spatial and channel attention mechanisms is proposed. Secondly, a detection head equipped with an attention mechanism is designed to intensify focus on small target information. Lastly, an adaptive weighted loss function is devised to improve detection performance for low-quality samples. Building upon these advancements, the network size can be further compressed to create the more lightweight YOLOv5-IRL version, which is better suited for deployment on resource-constrained mobile platforms. Experimental results on infrared dim and small target detection datasets with complex backgrounds indicate that, compared to the baseline model YOLOv5, the proposed YOLOv5-IR and YOLOv5-IRL detection algorithms reduce model parameter counts by 42.9% and 45.6%, shorten detection time by 13.6% and 16.9%, and enhance mAP0.5 by 2.4% and 1.8%, respectively. These findings demonstrate that the proposed algorithms effectively elevate detection efficiency, meeting future demands for infrared dim and small target detection. Full article

(This article belongs to the Special Issue The Recent Progression of Machine Learning in Remote Sensing: Theory and Modelling)

► Show Figures

Figure 1

22 pages, 29196 KiB

Open AccessArticle

MPG-Net: A Semantic Segmentation Model for Extracting Aquaculture Ponds in Coastal Areas from Sentinel-2 MSI and Planet SuperDove Images

by Yuyang Chen, Li Zhang, Bowei Chen, Jian Zuo and Yingwen Hu

Remote Sens. 2024, 16(20), 3760; https://doi.org/10.3390/rs16203760 - 10 Oct 2024

Abstract

Achieving precise and swift monitoring of aquaculture ponds in coastal regions is essential for the scientific planning of spatial layouts in aquaculture zones and the advancement of ecological sustainability in coastal areas. However, because the distribution of many land types in coastal areas [...] Read more.

Achieving precise and swift monitoring of aquaculture ponds in coastal regions is essential for the scientific planning of spatial layouts in aquaculture zones and the advancement of ecological sustainability in coastal areas. However, because the distribution of many land types in coastal areas and the complex spectral features of remote sensing images are prone to the phenomenon of ‘same spectrum heterogeneous objects’, the current deep learning model is susceptible to background noise interference in the face of complex backgrounds, resulting in poor model generalization ability. Moreover, with the image features of aquaculture ponds of different scales, the model has limited multi-scale feature extraction ability, making it difficult to extract effective edge features. To address these issues, this work suggests a novel semantic segmentation model for aquaculture ponds called MPG-Net, which is based on an enhanced version of the U-Net model and primarily comprises two structures: MS and PGC. The MS structure integrates the Inception module and the Dilated residual module in order to enhance the model’s ability to extract the features of aquaculture ponds and effectively solve the problem of gradient disappearance in the training of the model; the PGC structure integrates the Global Context module and the Polarized Self-Attention in order to enhance the model’s ability to understand the contextual semantic information and reduce the interference of redundant information. Using Sentinel-2 and Planet images as data sources, the effectiveness of the refined method is confirmed through ablation experiments conducted on the two structures. The experimental comparison using the FCN8S, SegNet, U-Net, and DeepLabV3 classical semantic segmentation models shows that the MPG-Net model outperforms the other four models in all four precision evaluation indicators; the average values of precision, recall, IoU, and F1-Score of the two image datasets with different resolutions are 94.95%, 92.95%, 88.57%, and 93.94%, respectively. These values prove that the MPG-Net model has better robustness and generalization ability, which can reduce the interference of irrelevant information, effectively improve the extraction precision of individual aquaculture ponds, and significantly reduce the edge adhesion of aquaculture ponds in the extraction results, thereby offering new technical support for the automatic extraction of aquaculture ponds in coastal areas. Full article

(This article belongs to the Special Issue Monitoring Coastal and Marine Environments Based on Remote Sensing Data)

► Show Figures

Figure 1

18 pages, 9898 KiB

Open AccessArticle

Land Cover Mapping in East China for Enhancing High-Resolution Weather Simulation Models

by Bingxin Ma, Yang Shao, Hequn Yang, Yiwen Lu, Yanqing Gao, Xinyao Wang, Ying Xie and Xiaofeng Wang

Remote Sens. 2024, 16(20), 3759; https://doi.org/10.3390/rs16203759 - 10 Oct 2024

Abstract

This study was designed to develop a 30 m resolution land cover dataset to improve the performance of regional weather forecasting models in East China. A 10-class land cover mapping scheme was established, reflecting East China’s diverse landscape characteristics and incorporating a new [...] Read more.

This study was designed to develop a 30 m resolution land cover dataset to improve the performance of regional weather forecasting models in East China. A 10-class land cover mapping scheme was established, reflecting East China’s diverse landscape characteristics and incorporating a new category for plastic greenhouses (totaling 8687.9 km² with 6340.5 km² in Shanghai specifically). Plastic greenhouses are key to understanding surface heterogeneity in agricultural regions, as they can significantly impact local climate conditions, such as heat flux and evapotranspiration, yet they are often not represented in conventional land cover classifications. This is mainly due to the lack of high-resolution datasets capable of detecting these small yet impactful features. For the six-province study area, we selected and processed Landsat 8 imagery from 2015–2018, filtering for cloud cover. Complementary datasets, such as digital elevation models (DEM) and nighttime lighting data, were integrated to enrich the inputs for the Random Forest classification. A comprehensive training dataset was compiled to support Random Forest training and classification accuracy. We developed an automated workflow to manage the data processing, including satellite image selection, preprocessing, classification, and image mosaicking, thereby ensuring the system’s practicality and facilitating future updates. We included three Weather Research and Forecasting (WRF) model experiments in this study to highlight the impact of our land cover maps on daytime and nighttime temperature predictions. The resulting regional land cover dataset achieved an overall accuracy of 83.2% and a Kappa coefficient of 0.81. These accuracy statistics are higher than existing national and global datasets. The model results suggest that the newly developed land cover, combined with a mosaic option in the Unified Noah scheme in WRF, provided the best overall performance for both daytime and nighttime temperature predictions. In addition to supporting the WRF model, our land cover map products, with a planned 3–5-year update schedule, could serve as a valuable data source for ecological assessments in the East China region, informing environmental policy and promoting sustainability. Full article

(This article belongs to the Topic Computer Vision and Image Processing, 2nd Edition)

► Show Figures

Figure 1

16 pages, 12210 KiB

Open AccessArticle

Analysis of the Influence of Different Reference Models on Recovering Gravity Anomalies from Satellite Altimetry

by Yu Han, Fangjun Qin, Hongwei Wei, Fengshun Zhu and Leiyuan Qian

Remote Sens. 2024, 16(20), 3758; https://doi.org/10.3390/rs16203758 - 10 Oct 2024

Abstract

A satellite altimetry mission can measure high-precision sea surface height (SSH) to recover a marine gravity field. The reference gravity field model plays an important role in this recovery. In this paper, reference gravity field models with different degrees are used to analyze [...] Read more.

A satellite altimetry mission can measure high-precision sea surface height (SSH) to recover a marine gravity field. The reference gravity field model plays an important role in this recovery. In this paper, reference gravity field models with different degrees are used to analyze their effects on the accuracy of recovering gravity anomalies using the inverse Vening Meinesz (IVM) method. We evaluate the specific performance of different reference gravity field models using CryoSat-2 and HY-2A under different marine bathymetry conditions. For the assessments using 1-mGal-accuracy shipborne gravity anomalies and the DTU17 model based on the inverse Stokes principle, the results show that CryoSat-2 and HY-2A using XGM2019e_2159 obtains the highest inversion accuracy when marine bathymetry is less than 2000 m. Compared with the EGM2008 model, the accuracy of CryoSat-2 and HY-2A is improved by 0.6747 mGal and 0.6165 mGal, respectively. A weighted fusion method that incorporates multiple reference models is proposed to improve the accuracy of recovering gravity anomalies using altimetry satellites in shallow water. The experiments show that the weighted fusion method using different reference models can improve the accuracy of recovering gravity anomalies in shallow water. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Ocean Observation (Third Edition))

► Show Figures

Figure 1

19 pages, 5199 KiB

Open AccessArticle

Enhanced Precipitation Nowcasting via Temporal Correlation Attention Mechanism and Innovative Jump Connection Strategy

by Wenbin Yu, Daoyong Fu, Chengjun Zhang, Yadang Chen, Alex X. Liu and Jingjing An

Remote Sens. 2024, 16(20), 3757; https://doi.org/10.3390/rs16203757 - 10 Oct 2024

Abstract

This study advances the precision and efficiency of precipitation nowcasting, particularly under extreme weather conditions. Traditional forecasting methods struggle with precision, spatial feature generalization, and recognizing long-range spatial correlations, challenges that intensify during extreme weather events. The Enhanced Temporal Correlation Jump Prediction Network [...] Read more.

This study advances the precision and efficiency of precipitation nowcasting, particularly under extreme weather conditions. Traditional forecasting methods struggle with precision, spatial feature generalization, and recognizing long-range spatial correlations, challenges that intensify during extreme weather events. The Enhanced Temporal Correlation Jump Prediction Network (ETCJ-PredNet) introduces a novel attention mechanism that optimally leverages spatiotemporal data correlations. This model scrutinizes and encodes information from previous frames, enhancing predictions of high-intensity radar echoes. Additionally, ETCJ-PredNet addresses the issue of gradient vanishing through an innovative jump connection strategy. Comparative experiments on the Moving Modified National Institute of Standards and Technology (Moving-MNIST) and Hong Kong Observatory Dataset Number 7 (HKO-7) validate that ETCJ-PredNet outperforms existing models, particularly under extreme precipitation conditions. Detailed evaluations using Critical Success Index (CSI), Heidke Skill Score (HSS), Probability of Detection (POD), and False Alarm Ratio (FAR) across various rainfall intensities further underscore its superior predictive capabilities, especially as rainfall intensity exceeds 30 dbz,40 dbz, and 50 dbz. These results confirm ETCJ-PredNet’s robustness and utility in real-time extreme weather forecasting. Full article

(This article belongs to the Special Issue Weather and Climate Extremes Monitoring Based on Remote Sensing Methods)

► Show Figures

Figure 1

30 pages, 27337 KiB

Open AccessArticle

Nested Cross-Validation for HBV Conceptual Rainfall–Runoff Model Spatial Stability Analysis in a Semi-Arid Context

by Mohamed El Garnaoui, Abdelghani Boudhar, Karima Nifa, Yousra El Jabiri, Ismail Karaoui, Abdenbi El Aloui, Abdelbasset Midaoui, Morad Karroum, Hassan Mosaid and Abdelghani Chehbouni

Remote Sens. 2024, 16(20), 3756; https://doi.org/10.3390/rs16203756 - 10 Oct 2024

Abstract

Accurate and efficient streamflow simulations are necessary for sustainable water management and conservation in arid and semi-arid contexts. Conceptual hydrological models often underperform in these catchments due to the high climatic variability and data scarcity, leading to unstable parameters and biased results. This [...] Read more.

Accurate and efficient streamflow simulations are necessary for sustainable water management and conservation in arid and semi-arid contexts. Conceptual hydrological models often underperform in these catchments due to the high climatic variability and data scarcity, leading to unstable parameters and biased results. This study evaluates the stability of the HBV model across seven sub-catchments of the Oum Er Rabia river basin (OERB), focusing on the HBV model regionalization process and the effectiveness of Earth Observation data in enhancing predictive capability. Therefore, we developed a nested cross-validation framework for spatiotemporal stability assessment, using optimal parameters from a donor-single-site calibration (DSSC) to inform target-multi-site calibration (TMSC). The results show that the HBV model remains spatially transferable from one basin to another with moderate to high performances (KGE (0.1~0.9 NSE (0.5~0.8)). Furthermore, calibration using KGE improves model stability over NSE. Some parameter sets exhibit spatial instability, but inter-annual parameter behavior remains stable, indicating potential climate change impacts. Model performance declines over time (18–124%) with increasing dryness. As a conclusion, this study presents a framework for analyzing parameter stability in hydrological models and highlights the need for more research on spatial and temporal factors affecting hydrological response variability. Full article

(This article belongs to the Special Issue Multi-Source Remote Sensing Data in Hydrology and Water Management)

► Show Figures

Figure 1

11 pages, 14937 KiB

Open AccessCommunication

The Value of Sentinel-1 Ocean Wind Fields Component for the Study of Polar Lows

by Eduard Khachatrian and Patricia Asemann

Remote Sens. 2024, 16(20), 3755; https://doi.org/10.3390/rs16203755 - 10 Oct 2024

Abstract

Polar lows can pose serious threats to maritime operations and coastal communities in polar regions, especially due to their extreme wind speeds. The accurate and reliable representation of their wind field thus plays a crucial role in forecasting and mitigating the risks associated [...] Read more.

Polar lows can pose serious threats to maritime operations and coastal communities in polar regions, especially due to their extreme wind speeds. The accurate and reliable representation of their wind field thus plays a crucial role in forecasting and mitigating the risks associated with this phenomenon. This study aims to evaluate the value of the SAR-based Sentinel-1 Ocean Wind Field product compared to two reanalysis products—regional CARRA and global ERA5—in studying the spatial wind speed distribution of polar lows. A visual comparison of the wind direction and wind speed fields was performed, as well as a brief quantitative analysis of wind speeds. Despite notable differences in spatial resolution, all of the data sources are able to identify the polar lows. However, the SAR-based product remains unmatched in capturing the intricate structure of the wind field. Although CARRA resolves more details than ERA5, it still deviates from the SAR image to a degree that suggests that the difference in spatial resolution is not the only source of disparity between the sources. Both CARRA and ERA5 underestimate the maximum wind speed as compared to the SAR data. Only the SAR data seems capable of providing the information necessary to study the details of the wind field of polar lows. Full article

(This article belongs to the Special Issue Remote Sensing of High Winds and High Seas)

► Show Figures

Figure 1

21 pages, 12594 KiB

Open AccessArticle

Remotely Sensed Estimation of Daily Near-Surface Air Temperature: A Comparison of Metop and MODIS

by Zhenwei Zhang, Peisong Li, Xiaodi Zheng and Hongwei Zhang

Remote Sens. 2024, 16(20), 3754; https://doi.org/10.3390/rs16203754 - 10 Oct 2024

Abstract

The estimation of spatially resolved near-surface air temperature (NSAT) has been extensively performed in previous studies using satellite-derived land surface temperature (LST) from MODIS. However, there remains a need for estimating daily NSAT based on LST data from other satellites, which has important [...] Read more.

The estimation of spatially resolved near-surface air temperature (NSAT) has been extensively performed in previous studies using satellite-derived land surface temperature (LST) from MODIS. However, there remains a need for estimating daily NSAT based on LST data from other satellites, which has important implications for integrating multi-source LST in estimating NSAT and ensuring the continuity of satellite-derived estimates of NSAT over long-term periods. In this study, we conducted a comprehensive comparison of LST derived from Metop with MODIS LST in the modeling and mapping of daily NSAT. The results show that Metop LST achieves consistent predictive performance with MODIS LST in estimating daily NSAT, and models based on Metop LST or MODIS LST have overall predictive performance of about 1.2–1.4 K, 1.5–2.0 K, and 1.8–1.9 K in RMSE for estimating Tavg, Tmax, and Tmin, respectively. Compared to models based on nighttime LST, daytime LST can improve the predictive performance of Tmax by about 0.26–0.28 K, while performance for estimating Tavg or Tmin using different schemes of LST is comparable. Models based on Metop LST also exhibit high consistency with models utilizing MODIS LST in terms of the variability in predictive performance across months, with RMSE of 1.03–1.82 K, 1.3–2.49 K, and 1.26–2.66 K for Tavg, Tmin, and Tmax, respectively. This temporal variability in performance is not due to sampling imbalance across months, which is confirmed by comparing models trained using bootstrapped samples in balance, and our results imply that sampling representativeness, complicated by retrieval gaps in LST, is an important issue when analyzing the variability in predictive performance for estimating NSAT. To fully assess the predictive capability of Metop LST in estimating daily NSAT, more studies need to be performed using different methods across areas with a range of scales and geographical environments. Full article

(This article belongs to the Special Issue Advances in Thermal Infrared Remote Sensing II)

► Show Figures

Figure 1

18 pages, 5571 KiB

Open AccessArticle

A Novel Pre-Processing Approach and Benchmarking Analysis for Faster, Robust, and Improved Small Object Detection Methods

by Mohammed Ali Mohammed Al-Hababi, Ahsan Habib, Fursan Thabit and Ying Liu

Remote Sens. 2024, 16(20), 3753; https://doi.org/10.3390/rs16203753 - 10 Oct 2024

Abstract

Detecting tiny objects in aerial imagery presents a major challenge regarding their limited resolution and size. Existing research predominantly focuses on evaluating average precision (AP) across various detection methods, often neglecting computational efficiency. Furthermore, state-of-the-art techniques can be complex and difficult to understand. [...] Read more.

Detecting tiny objects in aerial imagery presents a major challenge regarding their limited resolution and size. Existing research predominantly focuses on evaluating average precision (AP) across various detection methods, often neglecting computational efficiency. Furthermore, state-of-the-art techniques can be complex and difficult to understand. This paper introduces a comprehensive benchmarking analysis specifically tailored for enhancing small object detection within the DOTA dataset, focusing on one-stage detection methods. We propose a novel data-processing approach to enhance the overall AP for all classes in the DOTA-v1.5 dataset using the YOLOv8 framework. Our approach utilizes the YOLOv8’s darknet architecture, a proven effective backbone for object detection tasks. To optimize performance, we introduce innovative pre-processing techniques, including data formatting, noise handling, and normalization, in order to improve the representation of small objects and improve their detectability. Extensive experiments on the DOTA-v1.5 dataset demonstrate the superiority of our proposed approach in terms of overall class mean average precision (mAP), achieving 66.7%. Additionally, our method establishes a new benchmark regarding computational efficiency and speed. This advancement not only enhances the performance of small object detection but also sets a foundation for future research and applications in aerial imagery analysis, paving the way for more efficient and effective detection techniques. Full article

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

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sens., Volume 16, Issue 20 (October-2 2024) – 14 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI