Search Results (12,697)

Remote sensing images, which obtain surface information from aerial or satellite platforms, are of great significance in fields such as environmental monitoring, urban planning, agricultural management, and disaster response. However, due to the complex and diverse types of ground coverage and significant differences in spectral characteristics in remote sensing images, achieving high-quality semantic segmentation still faces many challenges, such as blurred target boundaries and difficulty in recognizing small-scale objects. To address these issues, this study proposes a novel deep learning model, MKF-NET. The fusion of KAN convolution and Vision Transformer (ViT), combined with the multi-scale feature extraction and dense connection mechanism, significantly improves the semantic segmentation performance of remote sensing images. Experiments were conducted on the LoveDA dataset to systematically evaluate the segmentation performance of MKF-NET and several existing traditional deep learning models (U-net, Unet++, Deeplabv3+, Transunet, and U-KAN). Experimental results show that MKF-NET performs best in many indicators: it achieved a pixel precision of 78.53%, a pixel accuracy of 79.19%, an average class accuracy of 76.50%, and an average intersection-over-union ratio of 64.31%; it provides efficient technical support for remote sensing image analysis. Full article

This study develops a geomorphological identification methodology for wall reefs in the microcontinental environment of Wangiwangi Island, Indonesia, using medium-resolution Landsat 8 satellite imagery and morphological analysis based on Maxwell’s geomorphological framework. The uniqueness of the wall reef landform lies in the fact that the lagoon elongates on limestone, resulting in a habitat and ecosystem that develops differently from those of other shelf reefs, namely, platform reefs and plug reefs. Using Optimum Index Factor (OIF) optimization and RGB image composites, four reef types were successfully identified: cuspate reefs, open ring reefs, closed ring reefs, and resorbed reefs. A field check was conducted at fifteen observation sites, which included measurements of depth, turbidity, and water quality parameters, as well as an in situ benthic habitat inventory. The analysis results showed a strong correlation between image composites, geomorphological reef classes, and ecological conditions, confirming the successful adaptation of Maxwell’s classification to the Indonesian reef system. This hybrid integrated approach successfully maps the distribution of reefs on a complex continental shelf, providing an essential database for shallow-water spatial planning, ecosystem-based conservation, and sustainable management in the Coral Triangle region. Policy recommendations include zoning schemes for protected areas based on reef landform morphology, strengthening integrative monitoring systems, and utilizing high-resolution imagery and machine learning algorithms in further research. Full article

There has been significant interest in deploying unmanned aerial vehicles (UAVs) for their ability to perform precise and rapid remote mapping and inspection of critical environmental assets for structural health monitoring. This case study investigates the use of UAV-based LiDAR and photogrammetry at Melbourne Water’s Western Treatment Plant (WTP) to routinely monitor high-density polyethylene floating covers on anaerobic lagoons. The proposed approach integrates LiDAR and photogrammetry data to enhance the accuracy and efficiency of generating digital elevation models (DEMs) and orthomosaics by leveraging the strengths of both methods. Specifically, the photogrammetric images were orthorectified onto LiDAR-derived DEMs as the projection plane to construct the corresponding orthomosaic. This method captures precise elevation points directly from LiDAR, forming a robust foundation dataset for DEM construction. This streamlines the workflow without compromising detail, as it eliminates the need for time-intensive photogrammetry processes, such as dense cloud and depth map generation. This integration accelerates dataset production by up to four times compared to photogrammetry alone, while achieving centimetre-level accuracy. The LiDAR-derived DEM achieved higher elevation accuracy with a root mean square error (RMSE) of 56.1 mm, while the photogrammetry-derived DEM achieved higher in-plane accuracy with an RMSE of up to 35.4 mm. An analysis of cover deformation revealed that the floating cover had elevated rapidly within the first two years post-installation before showing lateral displacement around the sixth year, which was also evident from a significant increase in wrinkling. This approach delivers valuable insights into cover condition that, in turn, clarifies scum accumulation and movement, thereby enhancing structural integrity management and supporting environmental sustainability at WTP by safeguarding methane-rich biogas for renewable-energy generation and controlling odours. The findings support the ongoing collaborative industry research between Monash University and Melbourne Water, aimed at achieving comprehensive structural and prognostic health assessments of these high-value assets. Full article

Fast and precise monitoring of soil organic matter (SOM) during maize growth periods is crucial for real-time assessment of soil quality. However, the big challenge we usually face is that many agricultural soils are covered by crops or snow, and the bare soil period is short, which makes reliable SOM prediction complex and difficult. In this study, an unmanned aerial vehicle (UAV) was utilized to acquire multi-temporal hyperspectral images of maize across the key growth stages at the field scale. The auxiliary predictors, such as spectral indices (I), field management (F), plant characteristics (V), and soil properties (S), were also introduced. We used stepwise multiple linear regression, partial least squares regression (PLSR), random forest (RF) regression, and XGBoost regression models for SOM prediction, and the results show the following: (1) Multi-temporal remote sensing information combined with multi-source predictors and their combinations can accurately estimate SOM content across the key growth periods. The best-fitting model depended on the types of models and predictors selected. With the I + F + V + S predictor combination, the best SOM prediction was achieved by using the XGBoost model (R² = 0.72, RMSE = 0.27%, nRMSE = 0.16%) in the R3 stage. (2) The relative importance of soil properties, spectral indices, plant characteristics, and field management was 55.36%, 26.09%, 9.69%, and 8.86%, respectively, for the multiple periods combination. Here, this approach can overcome the impact of the crop cover condition by using multi-temporal UAV hyperspectral images combined with valuable auxiliary variables. This study can also improve the field-scale farmland soil properties assessment and mapping accuracy, which will aid in soil carbon sequestration and soil management. Full article

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management. Full article

Soil organic carbon (SOC) is a crucial indicator of soil quality and carbon cycling. While remote sensing and machine learning enable regional scale SOC prediction, most studies rely on vegetation indices (VIs) derived from bare-soil periods, potentially neglecting vegetation–soil interactions during crop growth. Given the bidirectional relationship between SOC and crop growth, we hypothesized that using crop-lush period VIs (VIs_lush) instead of bare-soil period VIs (VIs_bare) would increase the inversion accuracy. To test this hypothesis, we chose the cropland area in Liaoning Province as the study area and developed three modeling strategies (MS-1: VIs_lush + other features; MS-2: VIs_bare + other features; and MS-3: without VIs) using Landsat 8 imagery, topographic and precipitation data, and ensemble learning models (XGBoost, RF, and AdaBoost), with SHapley Additive exPlanations (SHAP) analysis for variable interpretation. We found that (1) all models achieved their highest performance under MS-1, with XGBoost outperforming the others across all modeling strategies; (2) for XGBoost, MS-1 yielded the highest inversion accuracy (R² = 0.84, RMSE = 2.22 g·kg⁻¹, RPD = 2.49, and RPIQ = 3.25); compared with MS-2, MS-1 reduced the RMSE by 0.31 g·kg⁻¹, increased R² from 0.77 to 0.84, and reduced the RPD by 0.31 and the RPIQ by 0.40, and compared with MS-3, MS-1 reduced the RMSE by 0.41 g·kg⁻¹, increased R² from 0.79 to 0.84, and reduced the RPD by 0.39 and the RPIQ by 0.51; (3) based on the SHAP analysis of the three modeling strategies, it is considered that precipitation, terrain and terrain analysis results are important indicators for SOC content inversion, and it is confirmed that VIs_lush contributed more than VIs_bare, supporting the rationale of using lush-period imagery; and (4) Liaoning Province exhibited distinct SOC spatial patterns (mean: 13.08 g·kg⁻¹), with values ranging from 2.19 g·kg⁻¹ (sandy central–western area) to 33.86 g·kg⁻¹ (eastern mountains/coast). This study demonstrates that integrating growth stage-specific VIs with ensemble learning can significantly enhance regional-scale SOC prediction. Full article

Three-dimensional (3D) ocean physical fields are essential for understanding ocean dynamics, but reconstructing them solely from sea-surface remote sensing remains challenging. We present 3DV-Unet, an end-to-end deep learning framework that reconstructs eddy-resolving three-dimensional essential ocean variables (temperature, salinity, and currents) from multi-source satellite data. The model employs a 3D Vision Transformer bottleneck to capture cross-depth and cross-variable dependencies, ensuring physically consistent reconstruction. Trained on 2011–2019 reanalysis and satellite data, 3DV-Unet achieves RMSEs of ~0.30 °C for temperature, 0.11 psu for salinity, and 0.05 m/s for currents, with all R² values above 0.93. Error analyses further indicate higher reconstruction errors in dynamically complex regions such as the Kuroshio Extension, while spectral analysis indicates good agreement at 100 km+ but systematic deviation in the 20–100 km band. Independent validation against 6113 Argo profiles confirms its ability to reproduce realistic vertical thermohaline structures. Moreover, the reconstructed 3D fields capture mesoscale eddy structures and their life cycle, offering a valuable basis for investigating ocean circulation, energy transport, and regional variability. These results demonstrate the potential of end-to-end volumetric deep learning for advancing high-resolution 3D ocean reconstruction and supporting physical oceanography and climate studies. Full article

The aim of this study is to determine the reliability of regular and spatial cross-validation methods in predicting subfield-scale maize yields using phenological measures derived by Sentinel-2. Three maize fields from eastern Croatia were monitored during the 2023 growing season, with high-resolution ground truth yield data collected using combine harvester sensors. Sentinel-2 time series were used to compute two vegetation indices, Enhanced Vegetation Index (EVI) and Wide Dynamic Range Vegetation Index (WDRVI). These features served as inputs for three machine learning models, including Random Forest (RF) and Bayesian Generalized Linear Model (BGLM), which were trained and evaluated using both regular and spatial 10-fold cross-validation. Results showed that spatial cross-validation produced a more realistic and conservative estimate of the performance of the model, while regular cross-validation overestimated predictive accuracy systematically because of spatial dependence among the samples. EVI-based models were more reliable than WDRVI, generating more accurate phenomenological fits and yield predictions across parcels. These results emphasize the importance of spatially explicit validation for subfield yield modeling and suggest that overlooking spatial structure can lead to misleading conclusions about model accuracy and generalizability. Full article

Open-vocabulary object detection in remote sensing aims to detect novel categories not seen during training, which is crucial for practical aerial image analysis applications. While some approaches accomplish this task through large-scale data construction, such methods incur substantial annotation and computational costs. In contrast, we focus on efficient utilization of limited datasets. However, existing methods such as CastDet struggle with inefficient data utilization and class imbalance issues in pseudo-label generation for novel categories. We propose an enhanced open-vocabulary detection framework that addresses these limitations through two key innovations. First, we introduce a selective masking strategy that enables direct utilization of partially annotated images by masking base category regions in teacher model inputs. This approach eliminates the need for strict data separation and significantly improves data efficiency. Second, we develop a dynamic frequency-based class weighting that automatically adjusts category weights based on real-time pseudo-label statistics to mitigate class imbalance issues. Our approach integrates these components into a student–teacher learning framework with RemoteCLIP for novel category classification. Comprehensive experiments demonstrate significant improvements on both datasets: on VisDroneZSD, we achieve 42.7% overall mAP and 41.4% harmonic mean, substantially outperforming existing methods. On DIOR dataset, our method achieves 63.7% overall mAP with 49.5% harmonic mean. Our framework achieves more balanced performance between base and novel categories, providing a practical and data-efficient solution for open-vocabulary aerial object detection. Full article

Multi-modal image segmentation is a key task in various fields such as urban planning, infrastructure monitoring, and environmental analysis. However, it remains challenging due to complex scenes, varying object scales, and the integration of heterogeneous data sources (such as RGB, depth maps, and infrared). To address these challenges, we proposed a novel multi-modal segmentation framework, DyFuseNet, which features dynamic adaptive windows and cross-scale feature fusion capabilities. This framework consists of three key components: (1) Dynamic Window Module (DWM), which uses dynamic partitioning and continuous position bias to adaptively adjust window sizes, thereby improving the representation of irregular and fine-grained objects; (2) Scale Context Attention (SCA), a hierarchical mechanism that associates local details with global semantics in a coarse-to-fine manner, enhancing segmentation accuracy in low-texture or occluded regions; and (3) Hierarchical Adaptive Fusion Architecture (HAFA), which aligns and fuses features from multiple modalities through shallow synchronization and deep channel attention, effectively balancing complementarity and redundancy. Evaluated on benchmark datasets (such as ISPRS Vaihingen and Potsdam), DyFuseNet achieved state-of-the-art performance, with mean Intersection over Union (mIoU) scores of 80.40% and 80.85%, surpassing MFTransNet by 1.91% and 1.77%, respectively. The model also demonstrated strong robustness in challenging scenes (such as building edges and shadowed objects), achieving an average F1 score of 85% while maintaining high efficiency (26.19 GFLOPs, 30.09 FPS), making it suitable for real-time deployment. This work presents a practical, versatile, and computationally efficient solution for multi-modal image analysis, with potential applications beyond remote sensing, including smart monitoring, industrial inspection, and multi-source data fusion tasks. Full article

Accurate semantic segmentation of high-resolution remote sensing imagery is challenged by substantial intra-class variability, inter-class similarity, and the limitations of single-modality data. This paper proposes MMFNet, a novel multimodal fusion network that leverages the Mamba architecture to efficiently capture long-range dependencies for semantic segmentation tasks. MMFNet adopts a dual-encoder design, combining ResNet-18 for local detail extraction and VMamba for global contextual modelling, striking a balance between segmentation accuracy and computational efficiency. A Multimodal Feature Fusion Block (MFFB) is introduced to effectively integrate complementary information from optical imagery and digital surface models (DSMs), thereby enhancing multimodal feature interaction and improving segmentation accuracy. Furthermore, a frequency-aware upsampling module (FreqFusion) is incorporated in the decoder to enhance boundary delineation and recover fine spatial details. Extensive experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MMFNet achieves mean IoU scores of 83.50% and 86.06%, outperforming eight state-of-the-art methods while maintaining relatively low computational complexity. These results highlight MMFNet’s potential for efficient and accurate multimodal semantic segmentation in remote sensing applications. Full article

This study pioneers a fully remote sensing-based framework for mapping heatwave susceptibility, integrating the TabTransformer deep learning model with Particle Swarm Optimization (PSO) for robust hyperparameter tuning. The central question addressed is whether a fully remote sensing-driven, PSO-optimized TabTransformer can achieve accurate, scalable, and spatially detailed heatwave susceptibility mapping in data-scarce regions such as Central Asia. Utilizing ERA5-derived heatwave evidence and thirteen environmental and socio-economic predictors, the workflow produces high-resolution susceptibility maps spanning five Central Asian countries. Comparative analysis evidences that the PSO-optimized TabTransformer model outperforms the baseline across multiple metrics. On the test set, the optimized model achieved an RMSE of 0.123, MAE of 0.034, and R² of 0.938, outperforming the standalone TabTransformer (RMSE = 0.132, MAE = 0.038, R² = 0.93). Discriminative capacity also improved, with AUROC increasing from 0.933 to 0.940. The PSO-tuned model delivered faster convergence, lower final loss, and more stable accuracy during training and validation. Spatial outputs reveal heightened susceptibility in southern and southwestern sectors—Turkmenistan, Uzbekistan, southern Kazakhstan, and adjacent lowlands—with statistically significant improvements in spatial precision and class delineation confirmed by Chi-squared, Friedman, and Wilcoxon tests, all with congruent p-values of <0.0001. Feature importance analysis consistently identifies maximum temperature, frequency of hot days, and rainfall as dominant predictors. These advancements validate the potential of data-driven, deep learning approaches for reliable, scalable environmental hazard assessment, crucial for climate adaptation planning in vulnerable regions. Full article

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts. Full article

We investigate the applicability of visual foundation models, a recent advancement in artificial intelligence, for archaeological remote sensing. In contrast to earlier approaches, we employ a strictly zero-shot methodology, testing the hypothesis that such models can perform archaeological feature detection without any fine-tuning or other adaptation for the remote sensing domain. Across five experiments using satellite imagery, aerial LiDAR, and drone video data, we assess the models’ ability to detect archaeological features. Our results demonstrate that such foundation models can achieve detection performance comparable to that of human experts and established automated methods. A key advantage lies in the substantial reduction of required human effort and the elimination of the need for training data. To support reproducibility and future experimentation, we provide open-source scripts and datasets and suggest a novel workflow for remote sensing projects. If current trends persist, foundation models may offer a scalable and accessible alternative to conventional archaeological prospection. Full article

Real-time, accurate and detailed monitoring of urban green space is of great significance for constructing the urban ecological environment and maximizing ecological benefits. Although high-resolution remote sensing technology provides rich ground object information, it also makes the surface information of urban green spaces more complex. Existing classification methods often struggle to meet the requirements of classification accuracy and the automation demands of high-resolution images. This study utilized GF-7 remote sensing imagery to construct an urban green space classification method for Beijing. The study used the YOLO v8 model as the framework to conduct a fine classification of urban green spaces within the Fifth Ring Road of Beijing, distinguishing between evergreen trees, deciduous trees, shrubs and grasslands. The aims were to address the limitations of insufficient model fit and coarse-grained classifications in existing studies, and to improve vegetation extraction accuracy for green spaces in northern temperate cities (with Beijing as a typical example). The results show that the overall classification accuracy of the trained YOLO v8 model is 89.60%, which is 25.3% and 28.8% higher than that of traditional machine learning methods such as Maximum Likelihood and Support Vector Machine, respectively. The model achieved extraction accuracies of 92.92%, 93.40%, 87.67%, and 93.34% for evergreen trees, deciduous trees, shrubs, and grasslands, respectively. This result confirms that the combination of deep learning and high-resolution remote sensing images can effectively enhance the classification extraction of urban green space vegetation, providing technical support and data guarantees for the refined management of green spaces and “garden cities” in megacities such as Beijing. Full article