Search Results (488)

The selection of suitable sites for the disposal of radioactive waste constitutes a critical component of nuclear waste management. This study presents an original methodological proposal based on the Analytic Hierarchy Process (AHP), designed to support early-stage site screening for a near-surface repository in Italy. AHP could be used to identify appropriate locations, focusing on 51 areas that have already undergone a preliminary screening phase. These areas, included in the National Map of Suitable Areas (CNAI), were selected as they fulfill all the technical requirements (geological, geomorphological, and hydraulic stability) necessary to ensure the safety performance of the engineering structures to be implemented through multiple artificial barriers, as specified in Technical Guide N. 29. The proposed methodology is applicable in cases where multiple sites listed in the CNAI have been identified as potential candidates for hosting the repository. A panel of 20 multidisciplinary experts, including engineers, environmental scientists, sociologists, and economists, evaluated two environmental, two economic, and two social criteria not included among the criteria outlined in Technical Guide N. 29. Pairwise comparisons were aggregated using the geometric mean, and consistency ratios (CRs) were calculated to ensure the coherence of expert judgements. Results show that social criteria received the highest overall weight (0.53), in particular the “degree of site acceptability”, followed by environmental (0.28) and economic (0.19) criteria. While the method does not replace detailed site investigations (which will nevertheless be carried out once the site has been chosen), it can facilitate the early identification of promising areas and guide future engagement with local communities. The approach is reproducible, adaptable to additional criteria or national requirements, and may be extended to other countries facing similar nuclear waste management challenges. Full article

Defect detection in lithium-ion battery (LIB) welding presents unique challenges, including scale heterogeneity, subtle texture variations, and severe class imbalance. We propose a multi-scale convolutional framework that integrates EfficientNet-B0 for lightweight representation learning, PANet for cross-scale feature aggregation, and a YOLOv8 detection head augmented with multi-head attention. Parallel dilated convolutions are employed to approximate self-similar receptive fields, enabling simultaneous sensitivity to fine-grained microstructural anomalies and large-scale geometric irregularities. The approach is validated on three datasets including RIAWELC, GC10-DET, and an industrial LIB defects dataset, where it consistently outperforms competitive baselines, achieving 8–10% improvements in recall and F1-score while preserving real-time inference on GPU. Ablation experiments and statistical significance tests isolate the contributions of attention and multi-scale design, confirming their role in reducing false negatives. Attention-based visualizations further enhance interpretability by exposing spatial regions driving predictions. Limitations remain regarding fixed imaging conditions and partial reliance on synthetic augmentation, but the framework establishes a principled direction toward efficient, interpretable, and scalable defect inspection in industrial manufacturing. Full article

Contextual features play a critical role in geospatial object detection by characterizing the surrounding environment of objects. In existing deep learning-based studies of 3D point cloud classification and segmentation, these features have been represented through geometric descriptors, semantic context (i.e., modeled by an attention-based mechanism), global-level context (i.e., through global aggregation), and textural representation (e.g., RGB, intensity, and other attributes). Even though contextual features have been widely explored, spatial contextual features that explicitly capture spatial autocorrelation and neighborhood dependency have received limited attention in object detection tasks. This gap is particularly relevant in the context of GeoAI, which calls for mutual benefits between artificial intelligence and geographic information science. To bridge this gap, this study presents a spatial autocorrelation encoder, namely SA-Encoder, designed to inform 3D geospatial object detection by capturing spatial autocorrelation representation as types of spatial contextual features. The study investigated the effectiveness of such spatial contextual features by estimating the performance of a model trained on them alone. The results suggested that the derived spatial autocorrelation information can help adequately identify some large objects in an urban-rural scene, such as buildings, terrain, and large trees. We further investigated how the spatial autocorrelation encoder can inform model performance in a geospatial object detection task. The results demonstrated significant improvements in detection accuracy across varied urban and rural environments when we compared the results to models without considering spatial autocorrelation as an ablation experiment. Moreover, the approach also outperformed the models trained by explicitly feeding traditional spatial autocorrelation measures (i.e., Matheron’s semivariance). This study showcases the advantage of the adaptiveness of the neural network-based encoder in deriving a spatial autocorrelation representation. This advancement bridges the gap between theoretical geospatial concepts and practical AI applications. Consequently, this study demonstrates the potential of integrating geographic theories with deep learning technologies to address challenges in 3D object detection, paving the way for further innovations in this field. Full article

With the vigorous development of deep learning technology, lane detection tasks have achieved phased results. However, existing lane detection models do not consider the unique geometric and visual features of lanes when dealing with some challenging scenarios, resulting in many difficulties and limitations. To this end, we propose a lane detection network based on full-dimensional convolutional Transformer (OTVLD-Net) to improve the adaptability of the model under extreme road conditions and better handle complex lane topology. In order to extract richer contextual features, we designed ODVT-Net, which uses full-dimensional dynamic convolution combined with improved feature flip fusion layer and non-local network layer, and aggregates lane symmetry features by utilizing the horizontal symmetry of lanes. A feature weight generation mechanism based on Transformer is designed, and a cross-attention mechanism between feature maps and lane requests is added in the decoding stage to enable the network to aggregate global feature information. At the same time, a vanishing point detection module is introduced, and a joint weighted loss function is designed to be trained in coordination with the lane detection task to improve the generalization ability of the lane detection model. Experimental results on the OpenLane and CurveLanes datasets show that the detection effect of the OTVLD-Net model has reached the current advanced level. In particular, the accuracy on the OpenLane dataset is 6.4% higher than the F1 score of the second-ranked model, and the average performance in different challenging scenarios is also improved by 8.9%. At the same time, when ResNet-18 is used as the template feature extraction network, the model achieves a speed of 103FPS and a computing power of 14.2 GFlops, achieving good performance while ensuring real-time performance. Full article

Monocular Depth Estimation (MDE) remains a challenging problem due to texture ambiguity, occlusion, and scale variation in real-world scenes. While recent deep learning methods have made significant progress, maintaining structural consistency and robustness across diverse environments remains difficult. In this paper, we propose DAR-MDE, a novel framework that combines an autoencoder backbone with a Multi-Scale Feature Aggregation (MSFA) module and a Refining Attention Network (RAN). The MSFA module enables the model to capture geometric details across multiple resolutions, while the RAN enhances depth predictions by attending to structurally important regions guided by depth-feature similarity. We also introduce a multi-scale loss based on curvilinear saliency to improve edge-aware supervision and depth continuity. The proposed model achieves robust and accurate depth estimation across varying object scales, cluttered scenes, and weak-texture regions. We evaluated DAR-MDE on the NYU Depth v2, SUN RGB-D, and Make3D datasets, demonstrating competitive accuracy and real-time inference speeds (19 ms per image) without relying on auxiliary sensors. Our method achieves a $\delta$ < 1.25 accuracy of 87.25% and a relative error of 0.113 on NYU Depth v2, outperforming several recent state-of-the-art models. Our approach highlights the potential of lightweight RGB-only depth estimation models for real-world deployment in robotics and scene understanding. Full article

3D object detection is a crucial technology in fields such as autonomous driving and robotics. As a direct representation of the 3D world, point cloud data plays a vital role in feature extraction and geometric representation. However, in real-world applications, point cloud data often suffers from occlusion, resulting in incomplete observations and degraded detection performance. Existing methods, such as PG-RCNN, generate semantic surface points within each Region of Interest (RoI) using a single grid size. However, a fixed grid scale cannot adequately capture multi-scale features. A grid that is too small may miss fine structures—especially problematic when dealing with small or sparse objects—while a grid that is too large may introduce excessive background noise, reducing the precision of feature representation. To address this issue, we propose an enhanced PG-RCNN architecture with a Multi-Scale Grid Attention Module as the core contribution. This module improves the expressiveness of point features by aggregating multi-scale information and dynamically weighting features from different grid resolutions. Using a simple linear transformation, we generate attention weights to guide the model to focus on regions that contribute more to object recognition, while effectively filtering out redundant noise. We evaluate our method on the KITTI 3D object detection validation set. Experimental results show that, compared to the original PG-RCNN, our approach improves performance on the Cyclist category by 2.66% and 2.54% in the Moderate and Hard settings, respectively. Additionally, our approach shows more stable performance on small object detection tasks, with an average improvement of 2.57%, validating the positive impact of the Multi-Scale Grid Attention Module on fine-grained geometric modeling, and highlighting the efficiency and generalizability of our model. Full article

Point cloud segmentation underpins various applications in geospatial analysis, such as autonomous navigation, urban planning, and management. Kernel Point Convolution (KPConv) has become a de facto standard for such tasks, yet its fixed geometric kernel limits the modeling of fine-grained contextual relationships—particularly in heterogeneous, real-world point cloud data. In this paper, we introduce the adaptation of a Local Contextual Attention (LCA) mechanism for the KPConv network, with reweighting kernel coefficients based on local feature similarity in the spatial proximity domain. Crucially, our lightweight design preserves KPConv’s distance-based weighting while embedding adaptive context aggregation, improving boundary delineation and small-object recognition without incurring significant computational or memory overhead. Our comprehensive experiments validate the efficacy of the proposed LCA block across multiple challenging benchmarks. Specifically, our method significantly improves segmentation performance by achieving a 20% increase in mean Intersection over Union (mIoU) on the STPLS3D dataset. Furthermore, we observe a 16% enhancement in mean F1 score (mF1) on the Hessigheim3D benchmark and a notable 15% improvement in mIoU on the Toronto3D dataset. These performance gains place LCA-KPConv among the top-performing methods reported in these benchmark evaluations. Trained models, prediction results, and the code of LCA are available in a GitHub opensource repository. Full article

Digital ink Chinese characters (DICCs) written by international students often contain various errors and irregularities, making the recognition of these characters a highly challenging pattern recognition problem. This paper designs a graph convolutional network with agent attention (GCNAA) for recognizing DICCs written by international students. Each sampling point is treated as a vertex in a graph, with connections between adjacent sampling points within the same stroke serving as edges to create a Chinese character graph structure. The GCNAA is used to process the data of the Chinese character graph structure, implemented by stacking Block modules. In each Block module, the graph agent attention module not only models the global context between graph nodes but also reduces computational complexity, shortens training time, and accelerates inference speed. The graph convolution block module models the local adjacency structure of the graph by aggregating local geometric information from neighboring nodes, while graph pooling is employed to learn multi-resolution features. Finally, the Softmax function is used to generate prediction results. Experiments conducted on public datasets such as CASIA-OLWHDB1.0-1.2, SCUT-COUCH2009 GB1&GB2, and HIT-OR3C-ONLINE demonstrate that the GCNAA performs well even on large-category datasets, showing strong generalization ability and robustness. The recognition accuracy for DICCs written by international students reaches 98.7%. Accurate and efficient handwritten Chinese character recognition technology can provide a solid technical foundation for computer-assisted Chinese character writing for international students, thereby promoting the development of international Chinese character education. Full article

Vegetation restoration enhances soil erosion resistance by enhancing soil aggregates, but the function of these aggregates and their relationship with soil nutrients and microbes remain unclear. In this study, two land cover types that induce different aggregate ratios were selected to determine the soil aggregate ratio, aggregate ability, nutrients, and microbes. The results showed that high vegetation cover induced a higher macroaggregate ratio and soil water content; stronger soil shear strength; higher mean weight and geometric mean diameters; and lower soil bulk density. Macroaggregates had a lower soil organic matter (SOM) content compared with small macroaggregates. The aggregates and SOM influenced soil microbial diversity, especially microbial species and functions, and the large and small macroaggregate soils contained more microbes involved in SOM degradation, which accelerated the degradation and induced macroaggregate fragmentation. Total phosphorus (TP) had a direct impact on macroaggregates, and TP and macroaggregates showed the same correlation with the main microbial abundance. Taken together, we conclude that in the environment studied, SOM influenced soil microbes and the microbial function in SOM degradation affecting soil aggregates. TP contributed more to soil aggregate variations, especially in large macroaggregate formation. Full article

With the recent development of accurate protein structure prediction tools, virtually all protein sequences now have an experimental or a modeled structure. It has therefore become essential to develop fast algorithms capable of detecting non-covalent interactions not only within proteins but also in protein-protein, protein-DNA, protein-RNA, and protein-ligand complexes. Interactions involving aromatic compounds, particularly their $\pi$ molecular orbitals, hold unique significance among molecular interactions due to the electron delocalization, which is known to play a key role in processes such as protein aggregation. In this paper, we present PInteract, an algorithm that detects $\pi$-involving interactions in input structures based on geometric criteria, including $\pi$-$\pi$, cation-$\pi$, amino-$\pi$, His-$\pi$, and sulfur-$\pi$ interactions. In addition, it is capable of detecting chains and clusters of $\pi$ interactions as well as particular recurrent motifs at protein-DNA and protein-RNA interfaces, called stair motifs, consisting of a particular combination of $\pi$-$\pi$ stacking, cation/amino/His-$\pi$ and H-bond interactions. Full article

This study proposes a hierarchical framework with task priority perception for mission planning, to enhance multi-UAV coordination in maritime emergency search and rescue. By establishing a hierarchical decoupling optimization mechanism, the complex multi-region coverage problem is decomposed into two stages: task allocation and path planning. First, a coverage voyage estimation model is constructed based on regional geometric features to provide basic data for subsequent task allocation. Second, an improved multi-objective, multi-population grey wolf optimizer (IM2GWO) is designed to solve the task allocation problem; this integrates adaptive genetic operations and the multi-population coevolutionary mechanism. Finally, a globally optimal coverage path is generated based on the improved dynamic programming (DP). Simulation results indicate that the proposed method effectively reduces total task duration while boosting overall coverage benefits through the aggregation of high-value regions. IM2GWO demonstrates statistically superior performance with respect to the Pareto front distribution index across all test scenarios. Meanwhile, the path planning module based on DP can effectively reduce the overall coverage path cost. Full article

Soil structural instability in reservoir riparian zones, induced by water level fluctuations, threatens sustainable land use by accelerating land degradation. This study examined the impact of water-level variations on soil aggregate composition and stability based on key indicators, including water-stable aggregate content (WSAC), mean weight diameter (MWD), and geometric mean diameter (GMD). The Savinov dry sieving, Yoder wet sieving, and Le Bissonnais (LB) methods were employed for analysis. Results indicated that, with decreasing water levels and increasing soil layer, aggregates larger than 5 mm decreased, while aggregates smaller than 0.25 mm increased. Rising water levels and increasing soil layer corresponded to reductions in soil stability indicators (MWD, GMD, and WSAC), highlighting a trend toward soil structural instability. The LB method revealed the lowest aggregate stability under rapid wetting and the highest under slow wetting conditions. Correlation analysis showed that soil organic matter positively correlated with the relative mechanical breakdown index (RMI) (p < 0.05) and negatively correlated with the relative slaking index (RSI), whereas soil pH was negatively correlated with both RMI and RSI (p < 0.05). Comparative analysis of aggregate stability methods demonstrated that results from the dry sieving method closely resembled those from the SW treatment of the LB method, whereas the wet sieving method closely aligned with the FW (Fast Wetting) treatment of the LB method. The Le Bissonnais method not only reflected the outcomes of dry and wet sieving methods but also effectively distinguished the mechanisms of aggregate breakdown. The study concluded that prolonged flooding intensified aggregate dispersion, with mechanical breakdown influenced by water levels and soil layer. Dispersion and mechanical breakdown represent primary mechanisms of soil aggregate instability, further exacerbated by fluctuating water levels. By elucidating degradation mechanisms, this research provides actionable insights for preserving soil health, safeguarding water resources, and promoting sustainable agricultural in ecologically vulnerable reservoir regions of the Yangtze River Basin. Full article

The growing use of remote-sensing technologies has placed greater demands on object-detection algorithms, which still face challenges. This study proposes a hierarchical adaptive feature aggregation network (HAF-YOLO) to improve detection precision in remote-sensing images. It addresses issues such as small object size, complex backgrounds, scale variation, and dense object distributions by incorporating three core modules: dynamic-cooperative multimodal fusion architecture (DyCoMF-Arch), multiscale wavelet-enhanced aggregation network (MWA-Net), and spatial-deformable dynamic enhancement module (SDDE-Module). DyCoMF-Arch builds a hierarchical feature pyramid using multistage spatial compression and expansion, with dynamic weight allocation to extract salient features. MWA-Net applies wavelet-transform-based convolution to decompose features, preserving high-frequency detail and enhancing representation of small-scale objects. SDDE-Module integrates spatial coordinate encoding and multidirectional convolution to reduce localization interference and overcome fixed sampling limitations for geometric deformations. Experiments on the NWPU VHR-10 and DIOR datasets show that HAF-YOLO achieved mAP50 scores of 85.0% and 78.1%, improving on YOLOv8 by 4.8% and 3.1%, respectively. HAF-YOLO also maintained a low computational cost of 11.8 GFLOPs, outperforming other YOLO models. Ablation studies validated the effectiveness of each module and their combined optimization. This study presents a novel approach for remote-sensing object detection, with theoretical and practical value. Full article

In recent years, geographic knowledge graphs (GeoKGs) have shown great promise in representing spatio-temporal and event-driven knowledge. However, existing knowledge graph embedding approaches mainly focus on structural patterns and often overlook the dynamic evolution of entities in both time and space, which limits their effectiveness in downstream reasoning tasks. To address this, we propose a spatio-temporal evolutionary knowledge embedding approach (ST-EKA) that enhances entity representations by modeling their evolution through type-aware encoding, temporal and spatial decay mechanisms, and context aggregation. ST-EKA integrates four core components, including an entity encoder constrained by relational type consistency, a temporal encoder capable of handling both time points and intervals through unified sampling and feedforward encoding, a multi-scale spatial encoder that combines geometric coordinates with semantic attributes, and an evolutionary knowledge encoder that employs attention-based spatio-temporal weighting to capture contextual dynamics. We evaluate ST-EKA on three representative GeoKG datasets—GDELT, ICEWS, and HAD. The results demonstrate that ST-EKA achieves an average improvement of 6.5774% in AUC and 5.0992% in APR on representation learning tasks. In question answering tasks, it yields a maximum average increase of 1.7907% in AUC and 0.5843% in APR. Notably, it exhibits superior performance in chain queries and complex spatio-temporal reasoning, validating its strong robustness, good interpretability, and practical application value. Full article

In engineering and decision sciences, trapezoidal-valued neutrosophic fuzzy numbers $(TzVNFNs)$ have become effective tools for managing imprecision and uncertainty in multi-attribute group decision-making (MAGDM) problems. This work introduces accumulation operators based on the Dombi t-norm $(D{T}_n)$ and Dombi t-conorm $(D{T}_{cn})$ specifically designed for $TzVNFNs$. These operators enhance the flexibility, consistency, and fairness of the aggregation process. To demonstrate their practical applicability, we propose three novel geometric aggregation operator’s namely, the trapezoidal-valued neutrosophic fuzzy Dombi weighted geometric ($TzVNFDWG$), the trapezoidal-valued neutrosophic fuzzy Dombi ordered weighted geometric ($TzVNFDOWG$), and the trapezoidal-valued neutrosophic fuzzy Dombi hybrid Geometric ($TzVNFDHG$) operators. These are incorporated into a systematic MAGDM framework to support the selection of optimal locations for charging stations. Comparative analysis with current decision-making methodologies highlights the efficacy and benefits of the suggested method. The suggested method provides a flexible and mathematically based choice framework designed for uncertain condition. Full article