Search Results (168)

Tropical dry forests of mainland Southeast Asia contain considerable above-ground carbon (AGC) but present challenges for precise satellite-based AGC quantification because seasonal leaf phenology alters canopy reflectance throughout the year. To address this, we propose a phenology-informed approach that fuses multitemporal satellite imagery with airborne LiDAR. Using 17 PlanetScope images acquired between February 2024 and April 2026 over the Sakaerat Biosphere Reserve, together with UAV-LiDAR data, we extracted 128 phenological features and 12 canopy metrics at 10, 20 and 30 m. Machine learning models (Random Forest, XGBoost and LightGBM) were trained separately for dry evergreen forest (DEF) and dry dipterocarp forest (DDF). Under random five-fold cross-validation at 30 m, the best Random Forest models yielded R² = 0.681 (95% CI: 0.626–0.729) for DEF and R² = 0.661 (95% CI: 0.615–0.705) for DDF, with RMSE of 11.85 and 7.40 Mg C ha⁻¹, respectively. Because the AGC reference labels are themselves back-calculated from LiDAR canopy height, these Combined values partly reflect allometric circularity between predictors and labels and should be read as an upper bound rather than an independent accuracy; the spectral-only PlanetScope models, which are free of this circularity, give a more conservative R² = 0.342 (DEF) and 0.473 (DDF). Multitemporal phenological features and per-forest stratification jointly outperformed single-date baselines by 3.4× in DEF and 2.0× in DDF. We produced a 30 m AGC map of the reserve (total = 0.217 Tg C) and a higher resolution 3 m layer comprising ~8.7 million pixels. The results demonstrate the value of phenology-informed features and forest-type stratification for accurate AGC mapping in seasonally dry tropical forests, marking a step forward for remote sensing carbon assessment in phenologically dynamic landscapes. Full article

Seismically triggered landslides represent a major secondary hazard of earthquakes, often causing widespread damage over large areas. Rapid and reliable mapping of such phenomena is therefore essential, particularly in emergency contexts. While numerous studies have addressed landslide detection in vegetated regions using optical remote sensing, arid and desert environments remain relatively underexplored due to the limited spectral contrast between stable and failed slopes. In this study, we evaluate the potential of an automatic pixel-based method for the rapid detection of seismic landslides in arid settings, using high-resolution optical imagery. The analysis focuses on the Mw 5.5 earthquake that struck the Northern Red Sea Region of Eritrea on 26 December 2022. A detailed inventory of 1393 coseismic landslides was manually mapped from pre- and post-event PlanetScope multispectral images and used both for geomorphological and macroseismic analyses and as training data for a threshold-based classification approach. Landslide detection was based on changes in the Redness Soil Index (RSI) and its differential (ΔRSI), combined with a One-Class Asymmetric Robust Gaussian classifier. Results show a good capability to delineate landslide-affected areas, although commission errors remain significant. Despite these limitations, the proposed approach, still in need of a more trained implementation in the future, proves its potential effectiveness for rapid mapping purposes, owing to its simplicity and minimal computational requirements. These results open the possibility to implement a fully automatic methodology in the future, when more landslides will be mapped and a model trained on different and normalized datasets will be implemented. The results demonstrate that pixel-based optical methods, particularly those relying on red-band spectral changes, represent a valuable tool for the preliminary assessment of earthquake-induced landslides in arid environments and may support emergency response and first-order hazard evaluation. Full article

Timely landslide detection and rapid qualitative assessment are fundamental to effective warning systems, hazard management, and risk mitigation. Yet, current practices that rely on on-site surveys and manual expert assessment remain risky, costly, and time-consuming. These limitations result in substantial delays between the event and the availability of actionable information. This study proposes a hybrid, multi-model framework that fuses RGB remote-sensing imagery with geospatial layers to enable timely landslide detection and actionable reporting. The pipeline couples an enhanced SegFormer (denoted as SDF-SegFormer-B2) model for landslide localization, a feature extraction technique for per-slide geo-attribute computation, and a lightweight instruction-tuned LLM (Mistral-7B-Instruct-v0.3) for structured, expert-style reporting. Although a few previous studies have explored landslide captioning, to our knowledge this is the first framework designed to generate structured technical reports enriched with terrain-context interpretation and qualitative intervention-priority indicators. Experiments use 26,758 georeferenced RGB tiles (64 × 64) with 3 m of spatial resolution from PlanetScope satellite imagery over Emilia–Romagna, Italy, with 68,592 annotated landslide boxes collected after the May 2023 rainfall events (~200 mm in 48 h on 1–3 May; 200–250 mm in 48 h on 16–17 May). The proposed SDF-SegFormer-B2 segmentation model achieved a precision of 85.54%, recall of 72.31%, and an F1-score of 78.39% on the unseen test dataset. To evaluate the quality of the generated landslide reports, 100 images were selected for domain-expert assessment. Among these, 58% of the reports were rated as “Very Good,” 30% as “Good,” 8% as “Acceptable,” and 4% as “Poor.” When considering only reports with complete and accurate inputs, 81.48% were rated “Very Good,” and 96.30% were rated either “Good” or “Very Good.” By integrating complementary models and modalities, the proposed approach automates localization-to-reporting and enables the generation of terrain-aware landslide summaries that may support preliminary decision-making and rapid post-disaster screening. Full article

Generative deep learning-based synthetic aperture radar (SAR)-to-optical image translation (SOIT) has been widely employed for cloud removal. However, since cloud-contaminated regions reconstructed by SOIT inevitably contain prediction errors, an additional error refinement procedure is required to achieve reliable spectral reflectance reconstruction. In this study, three machine learning-based regression models, including Random Forest (RF), eXtreme Gradient Boosting (XGB), and Natural Gradient Boosting (NGB), are comprehensively evaluated for the error refinement of optical imagery initially reconstructed by SOIT. The factors influencing refinement performance are categorized into four components: (1) the sampling strategy of training pixels from cloud-free regions (random vs. quantile-based sampling); (2) the refinement target (actual spectral reflectance vs. residual between actual and initially reconstructed reflectance); (3) SAR features (pixel-level raw SAR features vs. local spatial SAR features); and (4) the cloud fraction in the scene of interest. A systematic sensitivity analysis of their effects on error refinement performance was conducted over cropland using PlanetScope optical imagery and COSMO-SkyMed SAR imagery. The results showed that cloud fraction had the greatest impact on refinement performance. Regarding SAR features for regression, the use of local spatial SAR features improved spectral similarity by up to approximately 4.6%p compared to raw SAR features. In terms of sampling strategy, quantile-based sampling yielded better refinement performance, whereas the effect of the refinement target was less pronounced. These results suggest that local spatial SAR features and quantile-based sampling strategies are the key determinants of regression-based refinement performance in SOIT-based cloud removal. Full article

Micro water bodies are essential to regional ecosystems but are difficult to extract from high-resolution remote sensing images due to fragmentation and building shadows. To address edge breakage and high false-alarm rates in existing semantic segmentation models, this study proposes MEF-TransUNet, an improved TransUNet-based model for fine micro water body extraction. The model integrates a multi-scale edge-guided attention module (MEGA), a high–low-frequency decomposition fusion module (HLFD), and a convolutional block attention module (CBAM). Specifically, MEGA extracts edge priors using a Laplacian pyramid to repair topological breaks in slender water bodies. HLFD uses frequency-domain decoupling to suppress high-frequency background noise and reduce confusion between water bodies and shadows. CBAM enhances channel and spatial feature attention. Experiments using PlanetScope images from the Songhuajiang River Basin in Daqing City of the Heilongjiang Province in China showed that MEF-TransUNet achieves 91.74% precision, a 90.07% F1-score, a recall of 90.22%, and a B-IoU of 43.88%. For the GID dataset, the model attains a precision of 91.85%, an F1-score of 91.48%, a recall of 92.01%, and a B-IoU of 55.42%. Its overall performance clearly outperforms DeepLabV3+, SegFormer, U-Net, AttenUNet, and UNet++, enabling accurate micro water body localization, high output purity, and reduced manual correction costs, thus supporting fine water resource management in complex surface environments. Full article

Precise mapping of rice cultivars is of great significance for crop management and food security evaluation. Nevertheless, differentiating between Indica and Japonica rice remains a formidable task, mainly due to subtle discrepancies in spectral characteristics and scattered planting distributions. This study evaluated the synergistic effect of spatial resolution and red edge information in rice variety classification using PlanetScope (PS) and Sentinel-2 (S2) images from the Tillering and Jointing stage, Heading and Flowering stage in Huai’an, Jiangsu Province. Multiple feature schemes were constructed, including spectral bands, vegetation indices, and texture features, with and without red-edge variables. A total of eight feature schemes have been constructed, including spectral bands, vegetation index, texture features, and red edge features. The feature scheme division is based on the participation of different sensors, growth periods, and red edges. We fine-tune three classification models, Random Forest (RF), Light Gradient Boosting Machine (LightGBM), and TabNet, to enhance classification performance. Additionally, we employ Shapley Additive Explanations (SHAP) to quantitatively measure the contribution of each feature to the prediction of distinct rice varieties. Results demonstrate that classification accuracy of different sensors reach the highest at the Heading and Flowering stage. The overall accuracy of PS scheme is 98.14%, the F1 scores of Japonica and Indica rice are 97.67% and 98.41%, the overall accuracy of S2 scheme is 97.87%, and the F1 scores of Japonica and Indica rice are 98.62% and 98.68, respectively. Incorporating red-edge features leads to a notable improvement in F1-scores for both Indica and Japonica rice under all experimental configurations. Although PS only has one red edge band set, its classification performance is similar to S2, and the boundaries between different rice variety recognition results and between non rice and rice plots are more refined compared to S2. Feature attribution analysis reveals that red-edge indices exert a dominant influence on the decision-making process of the models, especially during the Heading–Flowering period. These findings suggest that high-accuracy discrimination of rice varieties relies heavily on the synergistic optimization of phenological timing, red-edge spectral information, and spatial resolution, rather than merely increasing spectral dimensionality. The optimization direction for high-precision rice variety mapping in the future should prioritize the collaborative mechanism of phenological period, red edge data, and spatial resolution, rather than being limited to simple stacking in the spectral dimension. Full article

Flood monitoring in dry tropical basins, such as the Tumbes River (Peru), faces critical challenges due to persistent cloud cover that restricts the operability of optical sensors during extreme events, coupled with the operational gap between satellite products and conventional hydrological monitoring. To overcome these limitations, this research developed a comprehensive methodological framework in Google Earth Engine that unifies automated image thresholding and Sentinel-1 SAR time series analysis for flood detection and the estimation of early warning thresholds. The Bmax Otsu and Edge Otsu algorithms were evaluated, previously calibrated using high-resolution imagery (PlanetScope) as reference data, topographically constrained by the HAND (Height Above the Nearest Drainage) model, and validated against established change detection algorithms. The analysis of seven hydrological events between 2017 and 2024 confirmed the statistical superiority of Bmax Otsu; although both methods achieved high overall accuracy (Bmax 95.8% versus Edge 95.7%), Bmax Otsu outperformed Edge Otsu in spatial consistency (Kappa 66.1% vs. 63.7%; IoU 45.6% vs. 45.0%). Based on this, a time series analysis was applied to discriminate permanent water bodies and isolate flood dynamics. Subsequently, the functional discharge–impact response was evaluated by linking the instantaneous flood extent captured by the SAR overpasses to their corresponding peak discharges. Validated against official INDECI damage reports, it was determined that significant impacts begin at an activation threshold of 743.49 m³/s (151 flooded ha, 157 affected inhabitants) and scale linearly up to extreme peak events of 1629.02 m³/s, compromising 1234 agricultural ha and 749 inhabitants. This methodology provides a validated, low-cost tool to translate SAR observations into critical thresholds for early warning systems in data-scarce regions. Full article

High-resolution imagery is essential for monitoring heterogeneous grassland ecosystems, yet the performance of generative adversarial network (GAN) super-resolution under varying landscape heterogeneity and operational application scenarios remains unclear. This study presents a landscape-aware evaluation of super-resolution methods in semi-arid savanna grasslands of the Edwards Plateau (Texas, USA) using paired multispectral imagery from PlanetScope (3 m) and unmanned aerial vehicle (UAV) platforms (0.03 m). Two GAN models, SRGAN and ESRGAN, were compared with a bicubic interpolation baseline. Image tiles were systematically stratified along ecologically relevant gradients of vegetation condition (NDVI quartiles), spatial structure (woody patch-based clusters), and textural complexity (GLCM entropy quartiles). Model performance was evaluated across three operational frameworks: intra-sensor downscaling, cross-sensor downscaling, and intra-to-cross generalization. Reconstruction fidelity was quantified using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), complemented by variability analysis to assess performance stability. Landscape heterogeneity strongly influenced downscaling outcomes. SRGAN performance declined in areas with dense vegetation, aggregated woody structure, and high-entropy textures, with large variability under cross-sensor and generalization scenarios. In contrast, ESRGAN demonstrated consistently robust performance across landscape gradients, whereas bicubic interpolation performed well only under intra-sensor conditions and drastically degraded under sensor transfer. These results demonstrate that vegetation condition, structural heterogeneity, and sensor-transfer scenarios jointly constrain super-resolution performance. Rather than serving as a model comparison exercise, this study emphasizes a landscape-aware framework for understanding how ecological heterogeneity and operational domain shifts jointly shape super-resolution behavior in grassland ecosystems, providing guidance for more reliable applications of deep learning-based remote sensing methods. Full article

Coffee is among the primary agricultural commodities in international trade; however, mapping coffee crops in mountainous regions faces limitations due to high spectral variability and complex canopy structures. This study hypothesized that optimized spectral band combinations focused on the visible spectrum may outperform configurations including near-infrared (NIR) for coffee crop segmentation. This work aimed to evaluate how different spectral band combinations affect the performance of the U-Net for segmenting coffee crops in mountainous regions. Seven PlanetScope images (4 m resolution) from Matas de Minas, Brazil, covering different phenological stages in 2023–2024, were divided into 316 training patches and 25 test patches of 256 × 256 pixels and used to train U-Net models across five spectral band combinations: (B, G, R), (B, G, NIR), (B, R, NIR), (G, R, NIR), and (B, G, R, NIR). The visible spectrum combination (B, G, R) demonstrated superior performance with an overall Accuracy of 0.8669 and, for the Coffee Crops class, an F1-score of 0.8682 and an IoU of 0.7671, outperforming all NIR-inclusive configurations. Visible bands’ sensitivity to pigmentation variations proved more effective in heterogeneous environments, while NIR increased spectral confusion near native vegetation and crop edges. The model overestimated cultivated area by 18.3% due to mixed pixels from 4 m resolution and mountainous terrain. These findings confirm that visible-spectrum bands offer a cost-effective alternative for coffee segmentation, though higher spatial resolution is needed for improved boundary delineation. Full article

We investigate the potential of frequent repeat imagery acquired by the PlanetScope Dove small satellite constellation to overcome temporal and spatial limitations in automated surface topography mapping. While individual PlanetScope Dove stereo pairs produce low-quality Digital Surface Models (DSMs) with large height uncertainties, the high temporal frequency enables multiple DSMs to enhance accuracy through multiple-pair image matching. We present a fully automated SETSM framework by improving the quality of PlanetScope Dove DSMs based on SETSM Multi-Pair Matching Procedure (SETSM MMP). This framework enhances stereo pair quality through an optimized stereo pair selection by sequential conditional filtering and a Weighted Stereo Pair Index (WSPI). A novel inter-plane vertical coregistration, which minimizes scaling errors between single stereo pair DSMs, was developed to improve consistency and accuracy in DSM quality without reference surfaces. Applied to the cloud-obscured Pantasma crater region in Nicaragua, the optimized stereo pair selection automatically selects well-defined stereo pairs. The inter-plane vertical coregistration without existing reference surfaces achieves up to a 43% Root Mean Square Error (RMSE) reduction and 26% improvement in distribution within a 5 m vertical error. DSM quality correlated strongly with tile size, stereo pair convergence angle, asymmetric angle and terrain-dependent scale variability. The proposed framework provides fully automatic, high quality PlanetScope Dove DSMs without Ground Control Points (GCPs). Full article

Cropland constitutes a foundational resource for global food security and agricultural sustainability, and its accurate extraction from high-resolution remote sensing imagery is essential for agricultural monitoring and land management. However, existing deep learning-based segmentation methods often struggle to balance global contextual modeling and fine-grained boundary representation, leading to boundary blurring and omission of small cropland parcels. To address these challenges, this study proposes a novel CNN–Transformer dual-branch fusion network, named CAFM-Net, which integrates a convolution and attention fusion module (CAFM) and an edge-assisted supervision head (EH) to jointly enhance global–local feature interaction and boundary delineation capability. Experiments were conducted on a self-built PlanetScope cropland dataset from Suihua City, China, and the GID public dataset to evaluate the effectiveness and generalization ability of the proposed model. On the self-built dataset, CAFM-Net achieved an overall accuracy (OA) of 96.75%, an F1-score of 96.80%, and an Intersection over Union (IoU) of 93.79%, outperforming mainstream models such as UNet, DeepLabV3+, TransUNet, and Swin Transformer by a clear margin. On the GID public dataset, CAFM-Net obtained an OA of 94.58%, an F1-score of 94.19%, and an IoU of 89.02%, demonstrating strong robustness across different data sources. Ablation experiments further confirm that the CAFM contributes most significantly to performance improvement, while the EH module effectively enhances boundary accuracy. Overall, the proposed CAFM-Net provides a quantitatively validated and robust solution for fine-grained cropland segmentation from high-resolution remote sensing imagery, with clear advantages in boundary precision and small-parcel detection. Full article

The Yazoo–Mississippi Delta is an agricultural production zone and flyway for migratory birds. During winter, agricultural field-flooding practices are routinely used to support bird conservation and local recreational hunting opportunities. In response to the 2010 Deepwater Horizon oil spill, federal agencies incentivized flooding in summer and fall to mitigate the risks to migratory bird populations. This funding ceased in 2017, yet the United States Department of Agriculture Natural Resources Conservation Service Environmental Quality Incentives Program Practice 644 and a local non-profit continue to incentivize flooding during fall. Ensuring that contractual water levels are met is challenging to determine. To that end, we developed the Field Inundation Tool/Survey, an integrated remote sensing approach using PlanetScope imagery (Planet Labs, San Francisco, CA, USA) to quantify associated hydrology patterns. We used the Normalized Difference Water Index and an Iso Cluster Unsupervised Classification to estimate field inundation and associated habitat types over a three-year period. The results indicate dynamic field inundation can be estimated via PlanetScope imagery. Derived inundation metrics were comparable with in situ sensor and digital elevation models among some treatment types. We documented future refinements for image quality and soil patterns. Our work can improve conservation incentivization by tracking spatial and temporal patterns in adoption and has applicability to other agroecosystems. Full article

Intensifying urbanisation in the Arctic, particularly in spatially constrained coastal and island cities, requires reliable information on long-term land-use/land-cover (LULC) change to assess environmental impacts and support urban planning. However, multi-decadal, high-resolution LULC datasets for Arctic cities remain limited. In this study, we quantify LULC change on Tromsøya (Tromsø, Norway) from 1984 to 2024 using a Random Forest classifier applied to multispectral satellite imagery from Landsat and PlanetScope, complemented by LiDAR-derived canopy height models (CHM) and building footprints. We mapped LULC change trajectories and examined how these shifts relate to district-level population redistribution using gridded population data. The integration of a LiDAR-derived CHM was found to substantially improve the accuracy of Landsat-based LULC mapping and to represent the dominant source of classification gains, particularly for spectrally similar urban classes such as residential areas, roads, and other paved surfaces. Landsat augmented with CHM was shown to achieve practical equivalence to PlanetScope when the latter was modelled using spectral features only, supporting the feasibility of scalable and cost-effective long-term monitoring of urbanisation in Arctic cities. Based on the best-performing Landsat configuration, the proportions of artificial and green surfaces were estimated, indicating that approximately 20% of green areas were transformed into artificial classes. Spatially, population growth was concentrated in a small number of districts and broadly coincided with hotspots of green-to-artificial conversion The workflow provides a reproducible basis for long-term, district-scale LULC monitoring in small Arctic cities where data constraints limit the consistent use of high-resolution image. Full article

High-precision monitoring of arid wetlands is vital for ecological conservation, yet traditional methods incur prohibitive labeling costs due to complex features. In this study, the wetland of Bosten Lake in Xinjiang is selected as a case area, where Pleiades and PlanetScope-3 multimodal remote sensing data are fused using the Gram–Schmidt method to generate imagery with high spatial and spectral resolution. Based on this dataset, we systematically compare the performance of fully supervised models (FCN, U-Net, DeepLabV3+, and SegFormer) with a weakly supervised learning model, One Model Is Enough (OME), for classifying 19 wetland–cropland mosaic types. Results demonstrate that: (1) SegFormer achieved the best overall performance (98.75% accuracy, 95.33% mIoU), leveraging its attention mechanism to enhance semantic understanding of complex scenes. (2) The weakly supervised OME, using only image-level labels, matched fully supervised performance (98.76% accuracy, 92.82% F1-score) while drastically reducing labeling effort. (3) Multimodal fusion boosted all models’ accuracy, most notably increasing U-Net’s mIoU by 63.39%. (4) Models exhibited complementary strengths: U-Net excelled in wetland vegetation segmentation, DeepLabV3+ in crop classification, and OME in preserving spatial details. This study validates a pathway integrating multimodal fusion with WSL to balance high accuracy and low labeling costs for arid wetland mapping. Full article

Rice lodging is a major agricultural disaster that reduces yield and quality. Accurate lodging detection and causal analysis are essential for disaster mitigation and precision management. To overcome the limited coverage and low automation of conventional approaches, we propose MSR-LodfNet, an enhanced semantic-segmentation model driven by multi-scale remote-sensing imagery, enabling high-precision lodging mapping from regional to field scales. The study selected 13 state-owned farms in Jiansanjiang, Heilongjiang Province, and jointly used PlanetScope satellite images (3 m) and UAV images (0.2 m) to build an integrated workflow of “satellite macro-monitoring, UAV fine verification, and agronomic factor coupling analysis.” The model synergistically optimizes WFNet, DenseASPP multi-scale context enhancement, and Condensed Attention, markedly improving feature extraction and boundary recognition under multi-source imagery. Experimental results show that the model achieves mIoU 84.34% and mPA 93.31% on UAV images and mIoU 81.96% and mPA 90.63% on PlanetScope images, demonstrating excellent cross-scale adaptability and stability. Causal analysis shows that the high-EVI range is significantly positively correlated with lodging probability; its risk is about 6 times that of the low-EVI range, and the lodging probability of direct-seeded rice is about 2.56 times that of transplanted rice, indicating that it may be associated with a higher lodging risk. The results demonstrate that multi-scale remote sensing combined with agronomic parameters can effectively support the mechanism analysis of lodging disasters, providing a quantitative basis and technical reference for precision rice management and lodging-resistant breeding. Full article