Search Results (1,082)

Accurate solar forecasting is critical for photovoltaic integration, particularly in regions with complex terrain and limited observations. This study benchmarks five deep learning architectures—MLP, RNN, LSTM, CNN, and a Grey Wolf Optimizer–enhanced MLP (MLP–GWO)—to evaluate the accuracy–computational efficiency trade-off for generating daily solar potential maps from ERA5 reanalysis over Mexico. Models were trained using a strict temporal split on a high-dimensional grid (85 × 129 points, flattened to 10,965 outputs) and evaluated in terms of predictive skill and hardware cost. The RNN achieved the best overall performance (RMSE ≈ 32.3, MAE ≈ 27.8, R² ≈ 0.96), while the MLP provided a competitive lower-complexity alternative (RMSE ≈ 54.8, MAE ≈ 46.0, R² ≈ 0.88). In contrast, the LSTM and CNN showed poorer generalization, and the MLP–GWO failed to converge. For the CNN, this underperformance is linked to the intentionally flattened spatial representation. Overall, the results indicate that within a specific ERA5-based, daily-resolution, and resource-constrained experimental framework, lightweight architectures such as RNNs and MLPs offer the most favorable balance between accuracy and computational efficiency. These findings position them as efficient surrogates of ERA5-derived daily solar potential suitable for large-scale, preliminary energy planning applications. Full article

Almonds are a highly valued nut due to their rich protein and nutritional content. However, they are vulnerable to aflatoxin B1 (AFB1) contamination in warm and humid environments. Consumption of AFB1-contaminated almonds can pose serious health risks, including kidney damage, and may lead to significant economic losses. Consequently, a rapid and non-destructive detection method is essential to ensure food safety by identifying and removing contaminated almonds from the supply chain. Hyperspectral imaging (HSI) and 3D deep learning provide a non-destructive, efficient alternative to current AFB1 detection methods. This study presents an attention-guided Inception ResNet 3D Network (AGIR-3DNet) for fast and precise detection of AFB1 contamination in almonds utilizing HSI. The proposed model integrates multi-scale feature extraction, residual learning, and attention mechanisms to enhance spatial-spectral feature representation, enabling more precise classification. The proposed 3D model was rigorously tested, and its performance was compared against 3D Inception and various conventional machine learning models. Compared to conventional machine learning models and deep learning architectures, AGIR-3DNet outperformed and achieved superior validation accuracy of 93.30%, an F1-score (harmonic mean of precision and recall) of 0.94, and an area under the receiver operating characteristic curve (AUC) value of 0.98. Furthermore, the model enhances processing efficiency, making it faster and more suitable for real-time industrial applications. Full article

Monitoring microplastic pollution relies increasingly on bioindicators that integrate environmental exposure across habitats. This review presents animals explicitly proposed as microplastic bioindicators in recent literature and qualitatively evaluates their appropriateness using established biomonitoring criteria encompassing ecological, physiological, and methodological dimensions. In aquatic systems, bivalves (clams and mussels) demonstrate high suitability due to wide distribution, habitat-specific feeding, effective microplastic retention, and well-established analytical protocols. Fish exhibit intermediate suitability, as ecological representativeness and retention vary among species, and standardized methods often require multi-species approaches. Sessile organisms, including barnacles and sea anemones, align strongly with all three dimensions through spatial fidelity, effective retention, and methodological ease. Crustaceans and sponges also exhibit robust ecological relevance and high retention, with sponges uniquely integrating fine particles over time. Terrestrial and aerial indicators, such as carabid beetles and insectivorous birds, provide complementary coverage with moderate physiological integration and feasible ethical sampling. Sea turtles demonstrate exceptional physiological integration and methodological robustness at regional scales, despite non-sedentary behavior. Overall, taxa combining sedentary or spatially faithful ecology, effective microplastic retention, and standardized laboratory applicability, particularly bivalves, sponges, barnacles, sea anemones, and sediment-associated crustaceans, emerge as the most suitable bioindicators. Future research should prioritize harmonized, multi-taxa frameworks to improve standardization, cross-ecosystem comparability, and long-term microplastic monitoring. Full article

In view of the current remote sensing-based water body extraction research mostly relying on single data sources, being limited to specific water body types or regions, failing to leverage the advantages of multi-source data, and having difficulty in achieving large-scale, high-precision and rapid extraction, this paper integrates optical images and Synthetic Aperture Radar (SAR) data, and adopts an adaptive threshold segmentation method to propose a technical approach suitable for high-precision water body extraction on a monthly scale in large regions, which can efficiently extract water body information in large regions. Taking Beijing as the study area, the monthly spatial distribution of water bodies from 2019 to 2020 was extracted, and the pixel-level accuracy verification was carried out using the JRC Global Surface Water Dataset from the European Commission’s Joint Research Centre. The experimental results show that the water body extraction results are good, the extraction precision is generally higher than 0.8, and most of them can reach over 0.95. Finally, the method was applied to extract and analyze water body changes caused by heavy rainfall in Beijing in July 2025. This analysis further confirmed the effectiveness, accuracy, and practical utility of the proposed method. Full article

Ship detection in optical images is critical for maritime supervision but faces challenges from scale variations and complex backgrounds. Existing detectors often struggle to balance global context modeling with computational efficiency. To address this, we propose Contextual Efficient Hierarchical DETR (CEH-DETR), an efficient framework for multi-scale ship detection. First, we introduce the Cross-stage Parallel State Space Hidden Mixer (CPSHM) backbone, integrating State Space Models with CNNs to capture global dependencies with linear complexity. Second, the Efficient Adaptive Feature Integration (EAFI) module reduces attention complexity to linear using Token Statistics-based Attention. Third, the Hierarchical Attention-guided Feature Pyramid Network (HAFPN) effectively fuses multi-scale features while preserving spatial details. Experiments on the ABOships dataset demonstrate that CEH-DETR achieves a superior balance between accuracy and efficiency. Relative to the baseline RT-DETR, our approach achieves a parameter reduction of 25.6% while increasing mAP@50 by 2.0 percentage points and boosting inference speed to 133.7 FPS (+112.1%), making it highly suitable for real-time maritime surveillance. Full article

Recent large-kernel based SISR methods often struggle to balance global structural consistency with local texture preservation while maintaining computational efficiency. To address this, we propose the Hybrid Gated Large-kernel Network (HGLN). First, the Hybrid Multi-Scale Aggregation (HMSA) decouples features into structural and detailed streams via dual-path processing, utilizing a modified Large Kernel Attention to capture long-range interactions. Second, the Local–Global Synergistic Attention (LGSA) recalibrates features by integrating local spatial context with dual global statistics (mean and standard deviation). Finally, the Structure-Gated Feed-forward Network (SGFN) leverages high-frequency residuals to modulate the gating mechanism for precise edge restoration. Extensive experiments demonstrate that HGLN outperforms state-of-the-art methods. Notably, on the challenging Urban100 dataset ($\times 4$), HGLN achieves significant PSNR gains with extremely low complexity (only 11G Multi-Adds), proving its suitability for resource-constrained applications. Full article

Walkable urban environments are increasingly recognized as essential for sustainable mobility, public health, and social well-being. While macro-scale indicators of walkability are widely used, growing evidence highlights the importance of street-level physical conditions experienced at eye level. Advances in computer vision and street view imagery (SVI) offer new opportunities to quantify such streetscape characteristics, yet the applicability of existing semantic segmentation models in developing urban contexts remains underexplored. This study evaluates the suitability of five state-of-the-art semantic segmentation models for streetscape analysis using crowdsourced SVI from Phnom Penh, Cambodia. Through a comparative analysis, Oneformer was identified as the most suitable semantic segmentation model, uniquely successful in identifying street vendors through surrogate semantic class (base) and street furniture. A rigorous quantitative validation using manually annotated images confirmed the model’s reliability, achieving an mIoU of 65.7% within the complex urban fabric of Phnom Penh. This performance stems from OneFormer’s unified task-conditioned framework, which integrates semantic, instance, and panoptic information within a single query. Such an architecture ensures enhanced boundary stability and semantic coherence by consolidating visual noise into meaningful units, making it particularly robust for processing the irregular street elements typical of Southeast Asian cities. Applying the selected model revealed pronounced spatial variation in streetscape composition across three neighborhoods, reflecting distinct development stages and levels of informality. These findings suggest that carefully selected pretrained models can yield analytically useful representations of streetscape conditions in data-constrained settings, supporting more context-sensitive and inclusive urban analysis in rapidly developing cities. Full article

Leaf Area Index (LAI) is the total leaf area per unit of land surface area and is a crucial parameter for assessing vegetation growth and productivity. Machine learning regression algorithms are widely applied for LAI estimation. Due to spectral response variations among sensors and susceptibility of mangrove-derived variables to environmental noise suppression, obtaining sensitivity indices and optimal machine learning regression models is essential for retrieving mangrove LAI at the population scale. This study proposes a novel approach to processing and retrieving mangrove LAI data by integrating multispectral indices with machine learning methods. Box–Cox transformation and CatBoost-based feature selection were employed to obtain the optimal dataset. Random Forest (RF), Gradient Boosting Regression Trees (GBRT), and Categorical Boosting (CatBoost) algorithms were used to evaluate the accuracy of LAI retrieval from Unmanned Aerial Vehicle (UAV) and Gaofen-6 (GF-6) data. Results indicate that when LAI > 3, LAI does not immediately saturate as CVI, MTVI 2, and other indices increase, demonstrating higher sensitivity. UAV data outperformed GF-6 data in retrieving LAI for diverse mangrove populations; during model training, RF proved more suitable for small-sample datasets, while CatBoost effectively suppressed environmental noise. Both RF and CatBoost demonstrated higher robustness in estimating Avicennia marina (AM) (RF: R² = 0.704) and Aegiceras corniculatum (AC) (R² = 0.766), respectively. Spatial distribution analysis of LAI indicates that healthy AM and AC cover 85.36% and 96.67% of the area, respectively. Spartina alterniflora and aquaculture wastewater may be among the factors affecting the health of mangrove forests in the study area. LAI retrieval holds significant importance for mangrove health monitoring and risk early warning. Full article

The scarcity of land resources has become a bottleneck restricting the development of photovoltaic (PV) energy, and it is imperative to expand PV layout into the ocean. However, existing studies lack a refined site selection framework for large-scale sea areas. This study takes the Northwest Pacific coastal waters as the research area and constructs a three-stage evaluation framework for the suitability of offshore PV site selection, which includes “resource potential–spatial exclusion–multi-criteria assessment”. The results show that the theoretical power generation potential is generally “higher in the south and lower in the north”, with some deviations in local areas due to differences in temperature and wind speed. Only 4.3% of the sea area is feasible for development. The high-suitability areas are concentrated in the southeast coast of Vietnam and the northwest side of Taiwan Island. The South China Sea has superior development potential, while the Bohai Sea and the Yellow Sea are relatively less suitable. This study generates the first offshore PV site selection map covering the research area, providing a scientific basis for the formulation of differentiated development strategies for regional offshore PV. It has important practical value for promoting the sustainable development of blue energy. Full article

Nest-site selection in birds is a hierarchical process shaped by environmental filters operating across multiple spatial scales. In species that depend on burrows excavated by ecosystem engineers, understanding how these filters interact is essential for effective conservation. We evaluated nest-site selection by the Burrowing owl (Athene cunicularia) within colonies of the Mexican prairie dog (Cynomys mexicanus) in the southern Chihuahuan Desert using a multiscale analytical framework spanning burrow, site, colony, and landscape levels. During the 2010 and 2011 breeding seasons, we located 56 successful nests and paired each with an inactive non-nest burrow within the same colony. Eighteen structural and environmental variables were measured and analyzed using binary logistic regression models, with model selection based on an information-theoretic approach (AICc) and prior screening for predictor collinearity. Nest-site selection was associated with greater internal burrow development and reduced external exposure at the burrow scale, proximity to satellite burrows and low-to-moderate vegetation structure at the site scale, higher densities of active prairie dog burrows at the colony scale, and reduced predation risk and agricultural disturbance at the landscape scale. The integrated multiscale model showed substantially greater support and discriminatory power than single-scale models, indicating that nest-site selection emerges from interactions among spatial scales rather than from isolated factors. These findings support hierarchical habitat-selection theory and underscore the importance of conserving functional Mexican prairie dog colonies and low-disturbance grassland landscapes to maintain suitable breeding habitats for Burrowing owls in the southern Chihuahuan Desert. Full article

Skyros Island, the largest island of the Sporades Complex (NW Aegean Sea, Greece), preserves a geologically diverse record spanning from the Upper Permian to the Quaternary, including crystalline and non-metamorphosed carbonate rocks, ophiolitic rocks and mélanges, medium-grade metamorphic units, rare Miocene volcanic rocks, and impressive fossil-bearing sediments and tufa deposits, together with historically significant quarry and mining landscapes. Through a comprehensive evaluation of the geological heritage of Skyros, this study proposes a transferable, results-based framework for geoconservation, geoeducation, and tourism space management within a geopark context. A systematic inventory of twenty (20) geosites, including six (6) flagship case studies, was established based on scientific value, dominant geodiversity type, risk of degradation, accessibility, educational and tourism potential. The assessment integrates the Scientific Value and Risk of Degradation criteria with complementary management and sustainability indicators. The results demonstrate consistently high scientific value across the selected geosites, with several reaching maximum or near-maximum scores due to their rarity, integrity, and reference character at a regional to international scale. Although some geosites exhibit elevated degradation risk, overall vulnerability is considered manageable through targeted conservation measures and spatially explicit visitor management. Based on the assessment results, a network of thematic georoutes was developed and evaluated using route-level indicators, including number of geosites, route length, educational potential, tourism suitability, accessibility, and contribution to responsible geotourism. The study demonstrates how integrated geosite and georoute assessment can support sustainable land management and confirms that Skyros Island meets key criteria for inclusion in the Hellenic Geoparks Network, providing a robust scientific basis for future UNESCO Global Geopark designation. Full article

Background: Diagnosing CNS tumors through MRI is limited by significant variability in scanner hardware, acquisition protocols, and intensity characteristics at clinical centers, resulting in substantial domain shifts that lead to diminished reliability for automated models. Methods: We present a Domain-Adaptive MRI Learning Model (DA-MLM) consisting of an adversarially aligned hybrid 3D CNN–transformer encoder with contrastive regularization and covariance-based feature harmonization. Varying sequence MRI inputs ($T1$, $T1ce$, $T2$, and $FLAIR$) were inputted to multi-scale convolutional layers followed by global self-attention to effectively capture localized tumor structure and long-range spatial context, with domain adaptation that harmonizes feature distribution across datasets. Results: On the BraTS 2020 dataset, we found DA-MLM achieved 94.8% accuracy, 93.6% macro-F1, and 96.2% AUC, improving upon previously established benchmarks by 2–4%. DA-MLM also attained Dice score segmentation of 93.1% (WT), 91.4% (TC), and 89.5% (ET), improving upon 2–3.5% for CNN and transformer methods. On the REMBRANDT dataset, DA-MLM achieved 92.3% accuracy with segmentation improvements of 3–7% over existing U-Net and expert annotations. Robustness testing indicated 40–60% less degradation under noise, contrast shift, and motion artifacts, and synthetic shifts in scanner location showed negligible performance impairment (<0.06). Cross-domain evaluation also demonstrated 5–11% less degradation than existing methods. Conclusions: In summary, DA-MLM demonstrates improved accuracy, segmentation fidelity, and robustness to perturbations, as well as strong cross-domain generalization indicating the suitability for deployment in multicenter MRI applications where variation in imaging performance is unavoidable. Full article

Automated defect detection in printed circuit boards (PCBs) is a critical process for ensuring the quality and reliability of electronic products. To address the limitations of existing detection methods, such as insufficient sensitivity to minor defects and limited recognition accuracy in complex backgrounds, this paper proposes an enhanced YOLOv8 detection framework. The core contribution lies not merely in the integration of the Convolutional Block Attention Module (CBAM), but in a principled and task-specific integration strategy designed to address the multi-scale and low-contrast nature of PCB defects. The complete CBAM is integrated into the multi-scale feature layers (P3, P4, P5) of the YOLOv8 backbone network. By leveraging sequential channel and spatial attention submodules, CBAM guides the model to dynamically optimise feature responses, thereby significantly enhancing feature extraction for tiny, morphologically diverse defects. Experiments on a public PCB defect dataset demonstrate that the proposed model achieves a mean average precision (mAP@50) of 98.8% while maintaining real-time inference speed, surpassing the baseline YOLOv8 model by 9.5%, with the improvements of 7.4% in precision and 12.3% in recall. While the model incurs a higher computational cost (79.4 GFLOPs), it maintains a real-time inference speed of 109.11 FPS, offering a viable trade-off between accuracy and efficiency for high-precision industrial inspection. The proposed model demonstrates superior performance in detecting small-scale defects, making it highly suitable for industrial deployment. Full article

Rapid urbanization has exacerbated urban-stormwater challenges, highlighting the critical need for coordinated surface-water and groundwater management through rainfall recharge. However, current sponge city construction methods often overlook the crucial role of underground aquifers in regulating the water cycle and mostly rely on simplified engineering approaches. To address these limitations, this study proposes a spatial optimization framework for urban-scale sponge systems that integrates a hydrodynamic model (FVCOM), geographic information systems (GIS), and Monte Carlo simulations. This framework establishes a comprehensive evaluation system that synergistically integrates surface water inundation depth, geological lithology, and groundwater depth to quantitatively assess sponge city suitability. The FVCOM was employed to simulate surface water inundation processes under extreme rainfall scenarios, while GIS facilitated spatial analysis and data integration. The Monte Carlo simulation was utilized to optimize the spatial layout by objectively determining factor weights and evaluate result uncertainty. Using Shenzhen City in China as a case study, this research combined the “matrix-corridor-patch” theory from landscape ecology to optimize the spatial structure of the sponge system. Furthermore, differentiated planning and management strategies were proposed based on regional characteristics and uncertainty analysis. The research findings provide a replicable and verifiable methodology for developing sponge city systems in high-density urban areas. The core value of this methodology lies in its creation of a scientific decision-making tool for direct application in urban planning. This tool can significantly enhance a city’s climate resilience and facilitate the coordinated, optimal management of water resources amid environmental changes. Full article

Brown algal forests (Cystoseira sensu lato) are key habitat-forming components of temperate rocky coasts but have experienced widespread decline across the Mediterranean Sea. This study investigates the current distribution and potential future shifts in brown algal forests across the Adriatic Sea under ongoing climate change. We combined non-destructive field-based mapping along the Slovenian coastline with remote-sensing products and spatial environmental predictors to model basin-wide habitat suitability. A multiscale geographically weighted regression (MGWR) framework was applied to account for spatial non-stationarity and to explicitly capture the fact that environmental drivers of habitat suitability operate at different spatial scales—an assumption that global models such as GAM or standard GWR cannot adequately address. Habitat suitability maps were generated for present-day conditions and projected under mid- and late-century climate scenarios. The results reveal pronounced latitudinal gradients, identify areas of ongoing canopy decline in the northern Adriatic, and highlight parts of the southern Adriatic as potential climate refugia. Overall, the study demonstrates a likely north–south contraction of suitable habitat for brown algal forests and underscores the value of multiscale spatial modelling for informing marine spatial planning, conservation prioritization, and climate-adaptive restoration under European policy frameworks. Full article