Search Results (2,795)

The permanently shadowed regions of the lunar South Pole have become a key target for international lunar exploration due to their unique scientific value and engineering challenges. In order to effectively screen suitable landing zones near the lunar South Pole, this research proposes a comprehensive evaluation method based on a self-organizing map (SOM). Using multi-source remote sensing data, the method classifies and analyzes candidate landing zones by combining scientific purposes (such as hydrogen abundance, iron oxide abundance, gravity anomalies, water ice distance analysis, and geological features) and engineering constraints (such as Sun visibility, Earth visibility, slope, and roughness). Through automatic clustering, the SOM model finds the important regions. Subsequently, it integrates with a supervised learning model, a random forest, to determine the feature importance weights in more detail. The results from the research indicate the following: the areas suitable for landing account for 9.05%, 5.95%, and 5.08% in the engineering, scientific, and synthesized perspectives, respectively. In the weighting analysis of the comprehensive data, the weights of Earth visibility, hydrogen abundance, kilometer-scale roughness, and slope data all account for more than 10%, and these are thought to be the four most important factors in the automated site selection process. Furthermore, the kilometer-scale roughness data are more important in the comprehensive weighting, which is in line with the finding that the kilometer-scale roughness data represent both surface roughness from an engineering perspective and bedrock geology from a scientific one. In this study, a local examination of typical impact craters is performed, and it is confirmed that all 10 possible landing sites suggested by earlier authors are within the appropriate landing range. The findings demonstrate that the SOM-model-based analysis approach can successfully assess lunar South Pole landing areas while taking multiple constraints into account, uncovering spatial distribution features of the region, and offering a rationale for choosing desired landing locations. Full article

Accurate and efficient crop maps are essential for decision-makers to improve agricultural monitoring and management, thereby ensuring food security. The integration of advanced artificial intelligence (AI) models with hyperspectral remote sensing data, which provide richer spectral information than multispectral imaging, has proven highly effective in the precise discrimination of crop types. This systematic review examines the evolution of hyperspectral platforms, from Unmanned Aerial Vehicle (UAV)-mounted sensors to space-borne satellites (e.g., EnMAP, PRISMA), and explores recent scientific advances in AI methodologies for crop mapping. A review protocol was applied to identify 47 studies from databases of peer-reviewed scientific publications, focusing on hyperspectral sensors, input features, and classification architectures. The analysis highlights the significant contributions of Deep Learning (DL) models, particularly Vision Transformers (ViTs) and hybrid architectures, in improving classification accuracy. However, the review also identifies critical gaps, including the under-utilization of hyperspectral space-borne imaging, the limited integration of multi-sensor data, and the need for advanced modeling approaches such as Graph Neural Networks (GNNs)-based methods and geospatial foundation models (GFMs) for large-scale crop type mapping. Furthermore, the findings highlight the importance of developing scalable, interpretable, and transparent models to maximize the potential of hyperspectral imaging (HSI), particularly in underrepresented regions such as Africa, where research remains limited. This review provides valuable insights to guide future researchers in adopting HSI and advanced AI models for reliable large-scale crop mapping, contributing to sustainable agriculture and global food security. Full article

Landslides are among the most frequent geological hazards, often resulting in casualties and economic losses, particularly in alpine valley areas characterized by complex topography and dense vegetation. Landslides in these regions are distinguished by their high altitude, concealment, and sudden onset, which render traditional monitoring methods inefficient. This study proposes a landslide monitoring method for complex environments that leverages multi-source remote sensing data, incorporating the radiative transfer model and Small Baseline Subset-Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology. The proposed method was implemented to monitor the instability of the Baige landslide in Tibet, China. The results show that the vegetation Canopy Water Content (CWC) estimated using the radiative transfer model indirectly reflects landslide susceptibility. Specifically, excessive soil moisture from rainfall reduces oxygen in plant roots, affecting growth and lowering canopy water content. The region with lower Canopy Water Content (CWC < 0.04) exhibited an increasing trend in the number of pixels, rising from 271 to 549 before the landslide event, indicating poorer vegetation conditions in the area. Additionally, the SBAS-InSAR technique was utilized to extract surface displacement, achieving a maximum displacement of 112 mm during the monitoring period. Ultimately, the spatial changes of the two monitoring signals exhibited a high consistency. This study enhances the reliability of landslide displacement monitoring in complex environments and provides substantial scientific support for future large-scale monitoring efforts. Full article

Soil moisture (SM) profoundly influences crop growth, yield, soil temperature regulation, and ecological balance maintenance and plays a pivotal role in water resources management and regulation. The focal objective of this investigation is to identify feature parameters closely associated with soil moisture through the implementation of feature selection methods on multi-source remote sensing data. Specifically, three feature selection methods, namely SHApley Additive exPlanations (SHAP), information gain (Info-gain), and Info_gain ∩ SHAP were validated in this study. The multi-source remote sensing data collected from Sentinel-1, Landsat-8, and Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model (ASTGTM DEM) enabled the derivation of 25 characteristic parameters through sound computational approaches. Subsequently, a stacking algorithm integrating multiple machine-learning (ML) algorithms based on adaptive learning was engineered to accomplish soil moisture prediction. The attained prediction outcomes were then juxtaposed against those of single models, including Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). Notably, the adoption of feature factors selected by the Info_gain algorithm in combination with the adaptive stacking (Ada-Stacking) algorithm yielded the most optimal soil moisture prediction results. Specifically, the Mean Absolute Error (MAE) was determined to be 1.86 Vol. %, the Root Mean Square Error (RMSE) amounted to 2.68 Vol. %, and the R-squared (R2) reached 0.95. The multifactor integrated model that harnessed optical remote sensing data, radar backscatter coefficients, and topographic data exhibited remarkable accuracy in soil surface moisture retrieval, thus providing valuable insights for soil moisture inversion studies in the designated study area. Furthermore, the Ada-Stacking algorithm demonstrated its potency in integrating multiple models, thereby elevating retrieval accuracy and overcoming the limitations inherent in a single ML model. Full article

Unregulated underground group mining in China has led to problems such as unclear locations and complex shapes of mine goafs in mineral engineering, posing serious safety hazards for subsequent mining operations. This paper takes mineral engineering with complex mine goafs as the research object, integrates multi-survey data from surface deformation remote sensing monitoring and 3D laser scanning measurement to survey the area where the surface deformation rate reaches 14cm/ year, accurately identifies the location of risky mine goafs, and constructs detailed representations of the real shapes of the complex mine goafs inside the mineral engineering. The FLAC^3D 6.0 software is used to establish a 3D numerical simulation model of the mine goafs, fully considering the mining process, and conducting characteristic analysis of the stress distribution, failure range and surface deformation response of the mine goafs, revealing the impact of void deformation on the stability of the mine. The numerical simulation results are combined with on-site investigations to verify whether geological disasters have been caused by mine goafs. The research methods and results can provide effective technical means for the detailed survey and stability assessment of mineral engineering with complex mine goafs, which can help to reduce the risk of geological disasters in mines and improve the safety of mineral engineering. Full article

Unmanned aerial vehicle (UAV) remote sensing has emerged as a powerful tool for precision agriculture, offering high-resolution crop monitoring capabilities. However, multi-flight UAV missions introduce radiometric inconsistencies that hinder the accuracy of vegetation indices and physiological trait estimation. This study investigates the efficacy of relative radiometric correction in enhancing canopy chlorophyll content (CCC) estimation for winter wheat. Dual UAV sensor configurations captured multi-flight imagery across three experimental sites and key wheat phenological stages (the green-up, heading, and grain filling stages). Sentinel-2 data served as an external radiometric reference. The results indicate that relative radiometric correction significantly improved spectral consistency, reducing RMSE values (in spectral bands by >86% and in vegetation indices by 38–96%) and enhancing correlations with Sentinel-2 reflectance. The predictive accuracy of CCC models improved after the relative radiometric correction, with validation errors decreasing by 17.1–45.6% across different growth stages and with full-season integration yielding a 44.3% reduction. These findings confirm the critical role of relative radiometric correction in optimizing multi-flight UAV-based chlorophyll estimation, reinforcing its applicability for dynamic agricultural monitoring. Full article

The agro-pastoral ecotone of Gansu Province, a critical component of the ecological security barrier in northern China, is characterized by pronounced ecological fragility and climatic sensitivity. Investigating vegetation dynamics in this region is essential for balancing ecological conservation and sustainable development. This study integrated MODIS/NDVI remote sensing data (2000–2020), climate, land, and anthropogenic factors, employing Sen’s slope analysis, coefficient of variation (Cv), Hurst index, geodetector modeling, and partial correlation analysis to systematically unravel the spatio-temporal evolution and driving mechanisms of vegetation coverage. Key findings revealed the following: (1) Vegetation coverage exhibited a significant increasing trend (0.05 decade⁻¹), peaking in 2018 (NDVI = 0.71), with a distinct north–south spatial gradient (lower values in northern areas vs. higher values in southern regions). Statistically significant greening trends (p < 0.05) were observed in 55.42% of the study area. (2) Interannual vegetation fluctuations were generally mild (Cv = 0.15), yet central regions showed 2–3 times higher variability than southern/northwestern areas. Future projections (H = 0.62) indicated sustained NDVI growth. (3) Climatic factors dominated vegetation dynamics, with sunshine hours and precipitation exhibiting the strongest explanatory power (q = 0.727 and 0.697, respectively), while the elevation–precipitation interaction achieved peak explanatory capacity (q = 0.845). (4) NDVI correlated positively with precipitation in 43.62% of the region (r_mean = 0.47), whereas average temperature, maximum temperature, ≥10 °C accumulated temperature, and sunshine hours suppressed vegetation growth (r_mean = −0.06 to −0.42), confirming precipitation as the primary driver of regional vegetation recovery. The multi-scale analytical framework developed here provides methodological and empirical support for precision ecological governance in climate-sensitive transitional zones, particularly for optimizing ecological barrier functions in arid and semi-arid regions. Full article

Deep learning models have shown great potential in scientific research, particularly in remote sensing for monitoring natural resources, environmental changes, land cover, and land use. Deep semantic segmentation techniques enable land cover classification, change detection, object identification, and vegetation health assessment, among other applications. However, their effectiveness relies on large labeled datasets, which are costly and time-consuming to obtain. Domain adaptation (DA) techniques address this challenge by transferring knowledge from a labeled source domain to one or more unlabeled target domains. While most DA research focuses on single-target single-source problems, multi-target and multi-source scenarios remain underexplored. This work proposes a deep learning approach that uses Domain Adversarial Neural Networks (DANNs) for deforestation detection in multi-domain settings. Additionally, an uncertainty estimation phase is introduced to guide human review in high-uncertainty areas. Our approach is evaluated on a set of Landsat-8 images from the Amazon and Brazilian Cerrado biomes. In the multi-target experiments, a single source domain contains labeled data, while samples from the target domains are unlabeled. In multi-source scenarios, labeled samples from multiple source domains are used to train the deep learning models, later evaluated on a single target domain. The results show significant accuracy improvements over lower-bound baselines, as indicated by F1-Score values, and the uncertainty-based review showed a further potential to enhance performance, reaching upper-bound baselines in certain domain combinations. As our approach is independent of the semantic segmentation network architecture, we believe it opens new perspectives for improving the generalization capacity of deep learning-based deforestation detection methods. Furthermore, from an operational point of view, it has the potential to enable deforestation detection in areas around the world that lack accurate reference data to adequately train deep learning models for the task. Full article

Accurately monitoring forest canopy height is crucial for sustainable forest management, particularly in southeastern North Carolina, USA, where dense forests and limited accessibility pose substantial challenges. This study presents an explainable machine learning framework that integrates sparse GEDI LiDAR samples with multi-sensor remote sensing data to improve both the accuracy and interpretability of forest canopy height estimation. This framework incorporates multitemporal optical observations from Sentinel-2; C-band backscatter and InSAR coherence from Sentinel-1; quad-polarization L-Band backscatter and polarimetric decompositions from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR); texture features from the National Agriculture Imagery Program (NAIP) aerial photography; and topographic data derived from an airborne LiDAR-based digital elevation model. We evaluated four machine learning algorithms, K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and eXtreme gradient boosting (XGB), and found consistent accuracy across all models. Our evaluation highlights our method’s robustness, evidenced by closely matched R² and RMSE values across models: KNN (R² of 0.496, RMSE of 5.13 m), RF (R² of 0.510, RMSE of 5.06 m), SVM (R² of 0.544, RMSE of 4.88 m), and XGB (R² of 0.548, RMSE of 4.85 m). The integration of comprehensive feature sets, as opposed to subsets, yielded better results, underscoring the value of using multisource remotely sensed data. Crucially, SHapley Additive exPlanations (SHAP) revealed the multi-seasonal red-edge spectral bands of Sentinel-2 as dominant predictors across models, while volume scattering from UAVSAR emerged as a key driver in tree-based algorithms. This study underscores the complementary nature of multi-sensor data and highlights the interpretability of our models. By offering spatially continuous, high-quality canopy height estimates, this cost-effective, data-driven approach advances large-scale forest management and environmental monitoring, paving the way for improved decision-making and conservation strategies. Full article

The accurate extraction of mountainous cropland from remote sensing images remains challenging due to its fragmented plots, irregular shapes, and the terrain-induced shadows. To address this, we propose a deep learning framework, SE-ResUNet, that integrates Squeeze-and-Excitation (SE) modules into ResUNet to enhance feature representation. Leveraging Sentinel-1/2 imagery and DEM data, we fuse vegetation indices (NDVI/EVI), terrain features (Slope/TRI), and SAR polarization characteristics into 3-channel inputs, optimizing the network’s discriminative capacity. Comparative experiments on network architectures, feature combinations, and terrain conditions demonstrated the superiority of our approach. The results showed the following: (1) feature fusion (NDVI + TerrainIndex + SAR) had the best performance (OA: 97.11%; F1-score: 96.41%; IoU: 93.06%), significantly reducing shadow/cloud interference. (2) SE-ResUNet outperformed ResUNet by 3.53% for OA and 8.09% for IoU, emphasizing its ability to recalibrate channel-wise features and refine edge details. (3) The model exhibited robustness across diverse slopes/aspects (OA > 93.5%), mitigating terrain-induced misclassifications. This study provides a scalable solution for mountainous cropland mapping, supporting precision agriculture and sustainable land management. Full article

This review discusses the evolution and integration of open-access remote sensing technology in shoreline detection and coastal erosion monitoring through the use of Geographic Information Systems (GIS), Artificial Intelligence (AI), Unmanned Aerial Vehicles (UAVs), and Ground Truth Data (GTD). The Sentinel-2 and Landsat 8/9 missions are highlighted as the primary core datasets due to their open-access policy, worldwide coverage, and demonstrated applicability in long-term coastal monitoring. Landsat data have allowed the detection of multi-decadal trends in erosion since 1972, and Sentinel-2 has provided enhanced spatial and temporal resolutions since 2015. Through integration with GIS programs such as the Digital Shoreline Analysis System (DSAS), AI-based processes such as sophisticated models including WaterNet, U-Net, and Convolutional Neural Networks (CNNs) are highly accurate in shoreline segmentation. UAVs supply complementary high-resolution data for localized validation, and ground truthing based on GNSS increases the precision of the produced map results. The fusion of UAV imagery, satellite data, and machine learning aids a multi-resolution approach to real-time shoreline monitoring and early warnings. Despite the developments seen with these tools, issues relating to atmosphere such as cloud cover, data fusion, and model generalizability in different coastal environments continue to require resolutions to be addressed by future studies in terms of enhanced sensors and adaptive learning approaches with the rise of AI technology the recent years. Full article

Traditional methods for the construction of intertidal digital elevation models (DEMs) require the integration of long-term multi-sensor datasets and struggle to capture the spatiotemporal variation caused by ocean dynamics. The SWOT (surface water and ocean topography) mission, with its wide-swath interferometric altimetry technology, provides instantaneous full-swath elevation data in a single pass, offering a revolutionary data source for high-precision intertidal topographic monitoring. This study presents a framework for SWOT-based intertidal DEM extraction that integrates data preprocessing, topographic slope map construction, and tidal channel masking. The radial sand ridge region along the Jiangsu coast is analyzed using SWOT L2 LR (Low Resolution) unsmoothed data from July 2023 to December 2024. Multisource validation data are used to comprehensively assess the accuracy of sea surface height (SSH) and land elevation derived from LR products. Results show that the root mean square error (RMSE) of SSH at Dafeng, Yanghe, and Gensha tide stations is 0.25 m, 0.19 m, and 0.32 m, respectively. Validation with LiDAR data indicates a land elevation accuracy of ~0.3 m. Additionally, the topographic features captured by LR products are consistent with the patterns observed in the remote sensing imagery. A 16-month time-series analysis reveals significant spatiotemporal variations in the Tiaozini area, particularly concentrated in the tidal channel areas. Furthermore, the Pearson correlation coefficient for the DEMs generated from SWOT data decreased from 0.94 over a one-month interval to 0.84 over sixteen months, reflecting the persistent impact of oceanic dynamic processes on intertidal topography. Full article

Cloud removal is a vital preprocessing step in optical remote sensing images (RSIs), directly enhancing image quality and providing a high-quality data foundation for downstream tasks, such as water body extraction and land cover classification. Existing methods attempt to combine spatial and frequency features for cloud removal, but they rely on shallow feature concatenation or simplistic addition operations, which fail to establish effective cross-domain synergistic mechanisms. These approaches lead to edge blurring and noticeable color distortions. To address this issue, we propose a spatial–frequency collaborative enhancement Transformer network named SFCRFormer, which significantly improves cloud removal performance. The core of SFCRFormer is the spatial–frequency combined Transformer (SFCT) block, which implements cross-domain feature reinforcement through a dual-branch spatial attention (DBSA) module and frequency self-attention (FreSA) module to effectively capture global context information. The DBSA module enhances the representation of spatial features by decoupling spatial-channel dependencies via parallelized feature refinement paths, surpassing the performance of traditional single-branch attention mechanisms in maintaining the overall structure of the image. FreSA leverages fast Fourier transform to convert features into the frequency domain, using frequency differences between object and cloud regions to achieve precise cloud detection and fine-grained removal. In order to further enhance the features extracted by DBSA and FreSA, we design the dual-domain feed-forward network (DDFFN), which effectively improves the detail fidelity of the restored image by multi-scale convolution for local refinement and frequency transformation for global structural optimization. A composite loss function, incorporating Charbonnier loss and Structural Similarity Index (SSIM) loss, is employed to optimize model training and balance pixel-level accuracy with structural fidelity. Experimental evaluations on the public datasets demonstrate that SFCRFormer outperforms state-of-the-art methods across various quantitative metrics, including PSNR and SSIM, while delivering superior visual results. Full article

Accurate estimation of green canopy cover (GCC) in rubber plantations is crucial for monitoring vegetation health and assessing stress impacts. This study validates satellite-derived GCC estimates using unmanned aerial vehicle (UAV)-based remote sensing, ground observations, spaceborne remote sensing (satellite imagery), and supervised machine learning regression approaches. Sentinel-2 and Landsat imagery were utilized to derive spectral vegetation indices (SVIs) under varying stress conditions, while UAV-based GCC assessments provided high-resolution reference data for validation. The findings revealed that while certain SVIs exhibited strong correlations with canopy density under stable conditions, their predictive accuracy declined significantly during extreme stress events, such as Pestalotiopsis outbreaks and seasonal leaf fall periods. To improve estimation accuracy, supervised machine learning regression models were developed, with Random Forest (RF) outperforming Support Vector Machines (SVMs), Classification and Regression Trees (CARTs), and Linear Regression (LR). RF achieved the highest predictive accuracy (R² = 0.82, RMSE = 6.48, MAE = 4.97), demonstrating its reliability in capturing non-linear interactions between canopy heterogeneity and environmental stressors. These results highlight the limitations of traditional vegetation indices and emphasize the importance of multi-sensor integration and advanced modeling techniques for more precise GCC monitoring. Full article

The periodic rotation of the Ocean Color and Temperature Scanner (OCTS) introduces jitter errors in the HaiYang-3A (HY-3A) satellite, leading to internal geometric distortion in optical imagery and significant registration errors in multispectral images. These issues severely influence the application value of the optical data. To achieve near real-time compensation, a novel jitter error estimation and correction method based on multi-source attitude data fusion is proposed in this paper. By fusing the measurement data from star sensors and gyroscopes, satellite attitude parameters containing jitter errors are precisely resolved. The jitter component of the attitude parameter is extracted using the fitting method with the optimal sliding window. Then, the jitter error model is established using the least square solution and spectral characteristics. Subsequently, using the imaging geometric model and stable resampling, the optical remote sensing image with jitter distortion is corrected. Experimental results reveal a jitter frequency of 0.187 Hz, matching the OCTS rotation period, with yaw, roll, and pitch amplitudes quantified as 0.905”, 0.468”, and 1.668”, respectively. The registration accuracy of the multispectral images from the Coastal Zone Imager improved from 0.568 to 0.350 pixels. The time complexity is low with the single-layer linear traversal structure. The proposed method can achieve on-orbit near real-time processing and provide accurate attitude parameters for on-orbit geometric processing of optical satellite image data. Full article