Search Results (10,228)

Accurate mapping of rice cultivation is vital for ensuring food security, reducing greenhouse gas emissions, and achieving sustainable development goals. However, large-scale deep learning–based crop mapping remains limited due to the demand for vast, uniformly distributed, high-quality samples. To address this challenge, we propose a Progressive Deep Learning Crop Mapping (PDLCM) framework for national-scale, high-resolution rice mapping. Beginning with a small set of localized rice and non-rice samples, PDLCM progressively refines model performance through iterative enhancement of positive and negative samples, effectively mitigating sample scarcity and spatial heterogeneity. By combining time-series Sentinel-2 optical data with Sentinel-1 synthetic aperture radar imagery, the framework captures distinctive phenological characteristics of rice while resolving spatiotemporal inconsistencies in large datasets. Applying PDLCM, we produced 10 m rice maps from 2022 to 2024 across the middle and lower Yangtze River Basin, covering more than one million square kilometers. The results achieved an overall accuracy of 96.8% and an F1 score of 0.88, demonstrating strong spatial and temporal generalization. All datasets and source codes are publicly accessible, supporting SDG 2 and providing a transferable paradigm for operational large-scale crop mapping. Full article

Population activity drives urban development, and high-spatiotemporal-resolution population distribution provides critical insights for refined urban management and social services. However, mixed population activity patterns and spatial heterogeneity make simultaneous high-temporal- and -spatial-resolution estimation difficult. Therefore, we propose the High-Spatiotemporal-Resolution Population Distribution Estimation Based on the Strong and Weak Perception of Population Activity Patterns (SWPP-HSTPE) method to estimate hourly population distribution at the building scale. During the weak-perception period, we construct a Modified Dual-Environment Feature Fusion model using building features within small-scale grids to estimate stable nighttime populations. During the strong-perception period, we incorporate activity characteristics of weakly perceived activity populations (minors and older people). Then, the Self-Organizing Map algorithm and spatial environment function purity are used to decompose mixed patterns of strongly perceived activity populations (young and middle-aged) and to extract fundamental patterns, combined with building types, for population calculation. Results demonstrated that the SWPP-HSTPE method achieved high-spatiotemporal-resolution population distribution estimation. During the weak-perception period, the estimated population correlated strongly with actual household counts (r = 0.72) and outperformed WorldPop and GHS-POP by 0.157 and 0.133, respectively. During the strong-perception period, the SWPP-HSTPE model achieves a correlation with hourly population estimates that is approximately 4% higher than that of the baseline model, while reducing estimation errors by nearly 2%. By jointly accounting for temporal dynamics and population activity patterns, this study provides valuable data support and methodological insights for fine-grained urban management. Full article

In the context of mineral resource exploration, spatial prediction must cope with heterogeneous, non-normal data distributions and limited sampling. While conventional geostatistics and standard machine learning provide baseline estimates, they often suffer from excessive smoothing or fail to capture continuous spatial dependencies. This study proposes a geospatially aware Wasserstein conditional Generative Adversarial Network (GSA-cGAN) to complement existing workflows for multivariate mineral interpolation. The framework augments a baseline cGAN with WGAN-GP for stable adversarial training, CoordConv to encode absolute spatial coordinates and Self-Attention to capture long-range spatial dependencies. Eight model configurations were trained on 272 samples from a mineralized zone in the Taebaek Mountains, Korea, and strictly benchmarked against Ordinary/Universal Kriging and multivariate machine learning baselines (Random Forest, XGBoost). Under the adopted experimental design, the full GSA-cGAN achieved the lowest test root mean squared error and highest coefficient of determination, demonstrating a significant performance improvement over the baselines. Furthermore, distribution analysis confirmed that the model effectively overcomes the smoothing limitations of regression-based methods, generating high-resolution 10 m × 10 m maps that preserve statistical variance, hotspot anomalies, and complex spatial patterns. The results indicate that deep generative models can serve as practical decision-support tools for identifying drilling targets and prioritizing follow-up exploration in geologically complex settings. Full article

Seed phenomics is a critical research field for understanding seed germination mechanisms. Metasurfaces, composed of subwavelength nanostructures, offer a promising pathway to achieve both dispersion control and imaging functionalities within an ultra-compact form factor. Recent advances in micro–nano-optics and computational imaging have opened new avenues for high-dimensional, multimodal imaging. However, conventional hyperspectral and light-field systems still face limitations in compactness, depth resolution, and spectral–spatial integration. This review summarizes recent progress in metalens and metasurface lens array-based light-field systems for hyperspectral imaging and 3D reconstruction, with a focus on the underlying principles, design strategies, and reconstruction algorithms that enable single-shot 3D hyperspectral acquisition. We further present a forward-looking roadmap toward the realization of a revolutionized imaging paradigm: a metasurface-based light-field platform that fully integrates 3D and hyperspectral imaging capabilities. In particular, we examine how dispersive metasurfaces serve as core optical elements for precise dispersion control in hyperspectral imaging systems, while metalens arrays enable accurate modulation of spatial–angular distributions in light-field configurations. We systematically review both 3D and spectral reconstruction algorithms, highlighting their roles in decoding complex optical encodings. The application of these integrated systems in seed phenotyping is emphasized, demonstrating their capability to capture 3D spatial–spectral distributions in a single exposure. This approach facilitates high-throughput analysis of morphological traits, germination potential, and internal biochemical composition, offering a comprehensive solution for advanced seed characterization. Finally, we outline a practical roadmap for implementing a metasurface-based light-field platform that integrates hyperspectral imaging and computational 3D reconstruction. This review offers a comprehensive overview of the state of the art in compact 3D light-field systems and multimodal hyperspectral imaging platforms, while providing forward-looking insights aimed at advancing smart seed phenotyping, precision agriculture, and next-generation optical imaging technologies. Full article

The cotton boll opening rate (BOR) is an important indicator for evaluating the physiological maturation process of cotton and the critical stage of yield formation, and it provides essential guidance for subsequent defoliant application and mechanical harvesting. The investigation of cotton BOR usually relies on manual field surveys, which are time-consuming and destructive, making it difficult to achieve large-scale and efficient monitoring. UAV remote sensing technology has been widely used in crop growth monitoring due to its operational flexibility and high image resolution. However, because of the dense growth of the cotton canopy in UAV remote sensing imagery, the boll opening condition in the lower parts of the canopy cannot be completely observed. In contrast, UAV imagery can effectively monitor cotton leaf chlorophyll content (SPAD) and leaf area index (LAI), both of which undergo continuous changes during the boll opening process. Therefore, this study proposes using SPAD and LAI retrieved from UAV multispectral imagery as physiological intermediary variables to construct an empirical statistical equation and compare it with end-to-end machine learning baselines. Multispectral and ground synchronous data (n = 360) were collected in Baibi Town, Anyang, Henan Province, across four dates (8/28, 9/6, 9/13, 9/24). Twenty-eight commonly used vegetation indices were calculated from multispectral imagery, and Pearson’s correlation analysis was conducted to select indices sensitive to cotton SPAD, LAI, and BOR. Prediction models were constructed using the Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), and Partial Least Squares (PLS) models. The results showed that GBDT achieved the best prediction performance for SPAD (R² = 0.86, RMSE = 1.19), while SVM performed best for LAI (R² = 0.77, RMSE = 0.38). The quadratic polynomial equation constructed using SPAD and LAI achieved R² = 0.807 and RMSE = 0.109 in BOR testing, which was significantly better than the baseline model using vegetation indices to directly regress BOR. The method demonstrated stable performance in spatial mapping of BOR during the boll opening period and showed promising potential for guiding defoliant application and harvest timing. Full article

This study proposes a lightweight framework for transferring pretrained land cover classification architectures without additional training. The system utilizes French IGN imagery and Korean UAV and aerial imagery. It employs FLAIR U-Net models with ResNet34 and MiTB5 backbones, along with the AI-HUB U-Net. The implementation consists of four sequential stages. First, we perform class mapping between heterogeneous schemes and unify coordinate systems. Second, a quadratic polynomial regression equation is constructed. This formula uses multispectral band statistics as hyperparameters and class-wise IoU as the dependent variable. Third, optimal parameters are identified using the stationary point condition of Response Surface Methodology (RSM). Fourth, the final land cover map is generated by fusing class-wise optimal results at the pixel level. Experimental results show that optimization is typically completed within 60 inferences. This procedure achieves IoU improvements of up to 67.86 percentage points compared to the baseline. For automated application, these optimized values from a source domain are successfully transferred to target areas. This includes transfers between high-altitude mountainous and low-lying coastal territories via proportional mapping. This capability demonstrates cross-regional and cross-platform generalization between ResNet34 and MiTB5. Statistical validation confirmed that the performance surface followed a systematic quadratic response. Adjusted R² values ranged from 0.706 to 0.999, with all p-values below 0.001. Consequently, the performance function is universally applicable across diverse geographic zones, spectral distributions, spatial resolutions, sensors, neural networks, and land cover classes. This approach achieves more than a 4000-fold reduction in computational resources compared to full model training, using only 32 to 150 tiles. Furthermore, the proposed technique demonstrates 10–74× superior resource efficiency (resource consumption per unit error reduction) over prior transfer learning schemes. Finally, this study presents a practical solution for inference and performance optimization of land cover semantic segmentation on standard commodity CPUs, while maintaining equivalent or superior IoU. Full article

To address the issues of inadequate performance and excessive interaction costs when handling large-scale and complex-shaped change areas with existing interaction forms, this paper proposes RSICDNet, an interactive change detection (ICD) model with regional scribble interaction. In this framework, regional scribble interaction is introduced for the first time to provide rich spatial prior information for accurate ICD. Specifically, RSICDNet first employs an interaction processing network to extract interactive features, and subsequently utilizes the High-Resolution Network (HRNet) backbone to extract features from bi-temporal remote sensing images concatenated along the channel dimension. To effectively integrate these two information streams, an Interaction Fusion and Refinement Module (IFRM) is proposed, which injects the spatial priors from the interactive features into the high-level semantic features. Finally, an Object Contextual Representation (OCR) module is applied to further refine feature representations, and a lightweight segmentation head is used to generate final change map. Furthermore, a human–computer ICD application has been developed based on RSICDNet, significantly enhancing its potential for practical deployment. To validate the effectiveness of the proposed RSICDNet, extensive experiments are conducted against mainstream interactive deep learning models on the WHU-CD, LEVIR-CD, and CLCD datasets. The quantitative results demonstrate that RSICDNet achieves optimal Number of Interactions (NoI) metrics across all three datasets. Specifically, its NoI80 values reach 1.15, 1.45, and 3.42 on the WHU-CD, LEVIR-CD, and CLCD datasets, respectively. The qualitative results confirm a clear advantage for RSICDNet, which consistently delivers visually superior outcomes using the same or often fewer interactions. Full article

Hyperspectral imaging (HSI) captures the same scene across multiple spectral bands, providing richer spectral characteristics of materials than conventional RGB images. The spectral reconstruction task seeks to map RGB images into hyperspectral images, enabling high-quality HSI data acquisition without additional hardware investment. Traditional methods based on linear models or sparse representations struggle to effectively model the nonlinear characteristics of hyperspectral data. Although deep learning approaches have made significant progress, issues such as detail loss and insufficient modeling of spatial–spectral relationships persist. To address these challenges, this paper proposes the Cascaded Multi-Attention Feature Recurrent Enhancement Network (CMFREN). This method achieves targeted breakthroughs over existing approaches through a cascaded architecture of feature purification, spectral balancing and progressive enhancement. This network comprises two core modules: (1) the Hierarchical Residual Attention (HRA) module, which suppresses artifacts in illumination transition regions through residual connections and multi-scale contextual feature fusion, and (2) the Cascaded Multi-Attention (CMA) module, which incorporates a Spatial–Spectral Balanced Feature Extraction (SSBFE) module and a Spectral Enhancement Module (SEM). The SSBFE combines Multi-Scale Residual Feature Enhancement (MSRFE) with Spectral-wise Multi-head Self-Attention (S-MSA) to achieve dynamic optimization of spatial–spectral features, while the SEM synergistically utilizes attention and convolution to progressively enhance spectral details and mitigate spectral aliasing in low-resolution scenes. Experiments across multiple public datasets demonstrate that CMFREN achieves state-of-the-art (SOTA) performance on metrics including RMSE, PSNR, SAM, and MRAE, validating its superiority under complex illumination conditions and detail-degraded scenarios. Full article

Historical cropland reconstruction is crucial for modeling long-term agricultural dynamics and assessing their climatic and ecosystem impacts, while also providing critical regional benchmarks for improving global land-use datasets. This study presents a millennium-long reconstruction of cropland area at the provincial level for the Korean Peninsula by integrating multi-source historical cropland records, land surveys, and modern statistical and remote-sensing-based data. Then, a land suitability model for cultivation and a spatial allocation model were developed by incorporating topographic, climatic, and soil variables to generate 10 km resolution gridded cropland data over the past millennium. Our analysis revealed a long-term increasing trend in cropland area at the provincial level over the past millennium, with significant spatial and temporal variations. Spatially, cropland was primarily distributed in western coastal areas, with historical southward expansion. After the peninsula’s division, trends diverged, with continued growth in the north Korea but a decrease in the south Korea by 2000. The spatial allocation model validation results show strong spatial and quantitative agreement between the reconstructed historical cropland and the remote-sensing-based data, with 72.12% of grids differing by less than ±20%. This high consistency confirms the feasibility of the applied reconstruction method. Full article

Accurate characterization of seafloor sediment properties is critical for marine engineering design, resource assessment, and environmental management. Sidescan sonar offers efficient wide-area mapping capabilities, yet establishing robust quantitative relationships between acoustic backscatter intensity and sediment texture remains challenging, particularly in heterogeneous coastal environments. This study investigates the correlation between sidescan sonar backscatter intensity and sediment grain size parameters in waters southwest of Hainan Island, China. High-resolution acoustic data (450 kHz) were acquired alongside surface sediment samples from 18 stations spanning diverse sediment types. Backscatter intensity, represented by grayscale values, was systematically compared with grain size distributions and individual size fractions. Results reveal that mean grain size shows no meaningful correlation with backscatter intensity; however, fine sand fraction content (0.075–0.25 mm) exhibits a strong negative linear relationship (R² = 0.87 under optimal conditions). Distribution-level analysis demonstrates that backscatter variability mirrors sediment textural complexity, with coarse sediments producing broad, elevated intensity distributions and fine sediments yielding narrow, suppressed distributions. Inter-survey variability highlights the sensitivity of absolute intensity values to environmental conditions during acquisition. Spatial distribution analysis reveals that sediment grain size follows a systematic NE-SW gradient controlled by hydrodynamic energy, with notable local anomalies controlled by reef structures (producing coarse bioclastic sediment) and topographic sheltering (maintaining fine-grained deposits in shallow areas). These findings provide a quantitative basis for fraction-specific acoustic classification approaches while emphasizing the importance of multi-scale analysis incorporating both regional hydrodynamic trends and local morphological controls. The established relationship between fine sand abundance and acoustic response enables semi-quantitative sediment prediction from remotely sensed data, supporting improved seafloor mapping protocols for offshore infrastructure siting, aggregate resource evaluation, and coastal zone management in morphologically complex environments. Full article

Background: Mosquito-borne viral diseases are a growing global health threat, and artificial intelligence (AI) and machine learning (ML) are increasingly proposed as forecasting tools to support early-warning and response. However, the available evidence is fragmented across pathogens, settings and modelling approaches. This review provides, to the best of our knowledge, the first comprehensive comparative assessment of AI/ML models forecasting mosquito-borne viral diseases in human populations, jointly synthesising predictive performance across model families and appraising both methodological quality and operational readiness. Methods: Following PRISMA 2020, we searched PubMed, Embase and Scopus up to August 2025. We included studies applying AI/ML or statistical models to predict arboviral incidence, outbreaks or temporal trends and reporting at least one quantitative performance metric. Given the substantial heterogeneity in outcomes, predictors and time–space scales, we conducted a descriptive synthesis. Risk of bias and applicability were evaluated using PROBAST. Results: Ninety-eight studies met the inclusion criteria, of which 91 focused on dengue. The forecasts spanned national to city-level settings and annual-to-weekly resolutions. Across classification tasks, tree-ensemble models showed the most consistent performance, with accuracies typically above 0.85, while classical ML and deep-learning models showed wider variability. For regression tasks, errors increased with temporal horizon and spatial aggregation: short-term, fine-scale forecasts (e.g., weekly city level) often achieved low absolute errors, whereas long-horizon national models frequently exhibited very large errors and unstable performance. PROBAST assessment indicated that most studies (63/98) were at high risk of bias, with only 24 judged at low risk and limited external validation. Conclusions: AI/ML models, especially tree-ensemble approaches, show strong potential for short-term, fine-scale forecasting, but their reliability drops substantially at broader spatial and temporal scales. Most remain research-stage, with limited external validation and minimal operational deployment. This review clarifies current capabilities and highlights three priorities for real-world use: standardised reporting, rigorous external validation, and context-specific calibration. Full article

To strengthen the safety management and control of explosives in underwater blasting construction sites, this study proposes an improved YOLOv11-based network named CRS-Y, designed to enhance the detection accuracy of explosives in complex underwater environments and improve the recognition capability of multi-scale targets. To address the limitations of traditional object detection methods in handling complex backgrounds and low-resolution targets, a lightweight re-parameterized vision transformer was integrated into the C3K module, forming a novel CSP structure (C3K-RepViT) that enhances feature extraction under small receptive fields. In combination with the Efficient Multi-Scale Attention (EMSA) mechanism, the model’s spatial feature representation is further strengthened, enabling a more effective understanding of objects in complex scenes. Furthermore, to reduce the computational cost of the P2 feature layer, a new convolutional structure named SPD-DSConv (Space-to-Depth Depthwise Separable Convolution) is proposed, which integrates downsampling and channel expansion within depthwise separable convolution. This design achieves a balance between parameter reduction and multidimensional feature learning. Finally, the Inner-IoU loss function is introduced to dynamically adjust auxiliary bounding box scales, accelerating regression convergence for both high-IoU and low-IoU samples, thereby optimizing bounding box shapes and localization accuracy while improving overall detection performance and robustness. Experimental results demonstrate that the proposed CRS-Y model achieved superior performance on the VOC2012, URPC2020, and self-constructed underwater blasting datasets, effectively meeting the real-time detection requirements of underwater blasting construction scenarios while exhibiting strong generalization ability and practical value. Full article

The increasing availability of satellite data at different spatial resolutions offers new opportunities for environmental monitoring, highlighting the limitations of medium-resolution products for fine-scale territorial analysis. However, it also raises the need to enhance the resolution of low-quality imagery to enable more detailed spatial assessments. This study investigates the effectiveness of different super-resolution techniques applied to low-resolution (LR) multispectral Sentinel-2 satellite imagery to generate high-resolution (HR) data capable of supporting advanced knowledge extraction. Three main methodologies are compared: traditional bicubic interpolation, a generic Artificial Neural Network (ANN) approach, and a Convolutional Neural Network (CNN) model specifically designed for super-resolution tasks. Model performances are evaluated in terms of their ability to reconstruct fine spatial details, while the implications of these methods for subsequent visualization and environmental analysis are critically discussed. The evaluation protocol relies on RMSE, PSNR, SSIM, and spectral-faithfulness metrics (SAM, ERGAS), showing that the CNN consistently outperforms ANN and bicubic interpolation in reconstructing geometrically coherent structures. The results confirm that super-resolution improves the apparent spatial detail of existing spectral information, thus clarifying both the practical advantages and inherent limitations of learning-based super-resolution in Earth observation workflows. Full article

Urban lakes, as critical components of urban ecosystems, provide essential ecological services but face water quality deterioration due to rapid urbanization and associated land use changes. This study investigated the temporal and spatial characteristics and evolution mechanisms of water quality in Wuhan city lakes, with a focus on the Great East Lake basin (GELB), a typical urban lake cluster in the middle Yangtze River basin. By integrating monthly water quality monitoring data (2017–2023) with high-resolution land use data (2020), we employed the Water Quality Index (WQI), Spearman correlation analysis, and Redundancy Analysis (RDA) to assess water quality and the impact of land use on major pollutants. The results revealed significant spatial heterogeneity: Sha Lake (SL) exhibited the best water quality, while Yangchun Lake (YCL) and North Lake (NL) showed the worst conditions. Seasonal variations in water quality were observed, influenced by the ecological functions of lakes and surrounding land use. Notably, understanding these seasonal dynamics provides insights into nutrient cycle operations and their effective management under varying climatic conditions. In addition, the correlation between chlorophyll-a concentration and nutrient elements in urban lakes was not consistent, with some lakes showing significant negative correlations. The water quality of urban lakes is influenced by both land use and human management. Land use analysis indicated high impervious surfaces in East Lake (EL), SL, and YCL exacerbated runoff-driven nutrient loads, the nitrogen elevation from agricultural runoff of Yan East Lake (YEL) and NL’s pollution from historical industrial discharge. This study highlights the urgent need for targeted water management strategies to mitigate the impact of urbanization on water quality and provide a scientific basis for effective governance and ecological restoration in rapidly urbanizing areas around the world. By adopting an integrated approach combining water quality assessments with land use data, this research offers valuable insights for sustainable urban lake management. Full article

To address the high incidence of work-related musculoskeletal disorders (WMSDs) at manual edge-banding workstations in furniture factories, and in an effort to tackle the existing research challenges of poor cumulative risk quantification and inconsistent evaluations, this paper proposes a three-stage system for continuous, automated, non-invasive WMSD risk monitoring. First, MediaPipe 0.10.11 is used to extract 33 key joint coordinates, compute seven types of joint angles, and resolve missing joint data, ensuring biomechanical data integrity for subsequent analysis. Second, joint angles are converted into graded parameters via RULA, REBA, and OWAS criteria, enabling automatic calculation of posture risk scores and grades. Third, an Adaptive Pooling Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) dual-branch hybrid model based on the Efficient Channel Attention (ECA) mechanism is built, which takes nine-dimensional features as the input to predict expert-rated fatigue states. For validation, 32 experienced female workers performed manual edge-banding tasks, with smartphones capturing videos of the eight work steps to ensure authentic and representative data. The results show the following findings: (1) system ratings strongly correlate with expert evaluations, verifying its validity for posture risk assessment; (2) the hybrid model successfully captures the complex mapping of expert-derived fatigue patterns, outperforming standalone CNN and LSTM models in fatigue prediction—by integrating CNN-based spatial feature extraction and LSTM-based temporal analysis—and accurately maps fatigue indexes while generating intervention recommendations. This study addresses the limitations of traditional manual evaluations (e.g., subjectivity, poor temporal resolution, and inability to capture cumulative risk), providing an engineered solution for WMSD prevention at these workstations and serving as a technical reference for occupational health management in labor-intensive industries. Full article