Search Results (502)

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes. Full article

Administrative fragmentation, whereby political boundaries are used as analytical extents, can disrupt ecological flows and weaken ecological network planning by creating a mismatch between governance units and ecological processes. However, the pathways through which such fragmentation alters network structure and function remain insufficiently quantified. This study quantifies these effects and identifies the landscape conditions that shape the effectiveness of cross-boundary integration. Using a multi-scale buffer experiment (1–32 km) across 30 representative counties in China, we constructed ecological networks based on Morphological Spatial Pattern Analysis and on the minimum cumulative resistance model. Results show that relaxing administrative boundaries reduced structural distortions and lowered total ecological flow cost, indicating that fragmentation increases connectivity costs. Mechanistically, reducing redundant internal links and forced detours improved network efficiency mainly by shortening corridors and lowering flow costs, whereas mean corridor resistance changed little. This suggests that functional degradation is driven primarily by topological disruption rather than by declines in corridor quality. The benefits of cross-boundary integration were greater in counties with regular shapes, high grassland cover, humid climates, and rugged terrain, but weaker under strong human pressure and warmer temperatures. Improvements leveled off beyond 32 km, suggesting a 32 km buffer (study-specific) for integration and supporting context-specific strategies for ecological network planning. Full article

A design for a small chloride salt fast reactor (sm-MCFR) is presented through the integration of molten salt reactor and small reactor technologies, targeting efficient transmutation of transuranic (TRU) elements in spent nuclear fuel and rapid reactor deployment. The feasibility exploration and research on the design boundaries of sm-MCFR will be conducted in this article. The core adopts a dual-fluid configuration, in which the fuel salt and coolant circulate independently. Chloride salt is selected as the fuel carrier due to its high solubility for heavy metal nuclides and the low neutron absorption cross-section of chlorine, which help to form a hard fast-neutron spectrum and thereby enhance transmutation efficiency. The cooling system employs a direct supercritical carbon dioxide (s-CO₂) cycle, simplifying the overall layout. For the neutronics design, simulations were carried out using the TMCBurnup (TRITON MODEC Coupled Burnup Code). By adjusting the core geometry, fuel salt composition, and reprocessing strategy, the sm-MCFR achieves a hard fast-neutron spectrum but also demonstrates good potential for fuel utilization. In terms of thermal–hydraulic design, the heat exchange effect of the reactor core can be improved by adjusting the proportion of the coolant and the flow direction. The sm-MCFR is expected to become a promising candidate for advanced small reactors that have potential applications in nuclear waste transmutation and distributed energy generation. Full article

To address the recognition challenges caused by blurred state boundaries and the limitations of single monitoring modalities during aircraft skin laser paint stripping, this study proposes a multimodal data fusion method for state recognition based on laser-induced breakdown spectroscopy (LIBS) and surface imaging. By constructing a synchronous monitoring platform, a dataset covering five key physical states, namely topcoat (Tc), topcoat–primer transition (Tc-Pr), primer (Pr), primer–substrate transition (Pr-As), and substrate damage (As), was established. The proposed gated weighted multimodal fusion network (PGMF-Net) employs SE-ResNet1D to capture variations in elemental composition features from the spectra and integrates ResNet18 to extract changes in surface morphology from the images. The experimental results show that the proposed model outperforms the single-modal methods as well as the compared early-fusion and late-fusion methods, achieving a recognition accuracy of 94.12% on the test set and an average accuracy of 94.87% in stratified cross-validation. The bootstrap-based confidence interval analysis further verifies the stability of this method under the current dataset conditions. Further analysis indicates that the single-spectrum model has difficulty effectively distinguishing coating transition states because different transition states contain identical or highly similar characteristic peak information. The single-vision model, however, shows insufficient sensitivity to subtle substrate damage, whereas multimodal fusion enables complementary representation of material composition information and surface morphological information. Experimental validation under different power conditions further confirms that the model outputs are generally consistent with the macroscopic morphological evolution observed on the sample surface. This method compensates for the limitations of traditional single-source monitoring and provides a methodological foundation for online monitoring and state feedback during the laser paint stripping process. Full article

In the field of subgrade compaction quality assessment, accurate volume measurement of excavated pits is hindered by non-uniform point cloud distribution, environmental noise interference, and complex irregular boundary features. To address these challenges, this paper proposes a robust volume detection framework that integrates adaptive point cloud refinement and morphological discrimination. First, a pose normalization method employing RANSAC plane fitting and rigid body transformation corrects the spatial orientation of the raw point clouds. To balance data redundancy removal with feature preservation, a gradient adaptive simplification strategy based on local density feedback and K-nearest neighbor estimation is developed. Subsequently, a cross-sectional area calculation model utilizing piecewise-cubic polynomial fitting is proposed to mitigate boundary noise and accurately reconstruct irregular contours. Furthermore, a dynamic outlier removal mechanism based on the Median Absolute Deviation (MAD) and sliding windows is introduced to eliminate non-physical geometric fluctuations. Finally, the total volume is aggregated using a hybrid strategy of Simpson’s rule and a frustum compensation operator. Experimental results on simulated pits with typical topological defects demonstrate that the proposed algorithm outperforms traditional methods, achieving an average relative volume error of less than 0.8%. This approach significantly improves the robustness and precision of sensor-based automated subgrade compaction quality measurement. Full article

Plant mitochondrial genomes are difficult to analyze because of their structural dynamism and frequent annotation errors. To address these challenges, we first constructed a high-confidence mitochondrial reference library for Rhodiola by integrating transcriptomic evidence, public sequence resources, and experimental validation. This curated resource defined 30 mitochondrial protein-coding genes (PCGs), including corrected exon–intron boundaries and validated 5′-terminal variants in ccmC, ccmFn, and nad9. Leveraging this curated dataset, we developed the RhoMitoAnnotator, which integrates three novel algorithms, EBAnno, REAnno, and NCAnno, to accurately annotate trans-splicing, RNA editing, and non-canonical start/stop codons. Using long-read sequencing guided by the RhoMitoAnnotator, we completed the mitogenomes of R. rosea, R. crenulata, and R. sacra, systematically re-annotated seven publicly available mitogenomes, revealing cross-chromosomal gene arrangement, and widespread structural misannotations. To enable scalable analysis with short-read data, we built Polypods, an integrated pipeline that successfully assembled mitochondrial PCGs from 108 samples across 39 Rhodiola species, and identified variant genes, stop codon-lacking regions in nad6, and internal stop codons in rpl16. Phylogenetic analyses based on mitochondrial and chloroplast PCGs showed a lineage pattern consistent with the hypothesis of an evolutionary transition from hermaphroditism to dioecy in Rhodiola, and consistently supported six species as monophyletic lineages. Overall, this study provides a curated mitochondrial gene atlas for Rhodiola and a reference-guided analytical framework for mitochondrial PCG annotation and recovery in this genus, with potential adaptability to other plant lineages after lineage-specific database construction and parameter optimization. Full article

The high-density integration of low-temperature co-fired ceramic (LTCC) filters inevitably induces complex parasitic coupling. Traditional designs rely on forced isolation to mitigate this issue, often at the expense of increased physical footprints. To overcome this limitation, this paper proposes a strategy for the controlled utilization of parasitic effects. Methodologically, localized grounding structures are introduced to construct a controlled electromagnetic boundary. The system’s main path exhibits alternating inductive-capacitive (L-C) coupling, with a single explicit capacitive cross-coupling introduced between specific nodes (resonators 2 and 5). Based on the principle of multi-path signal cancellation, this explicit path synergizes with the implicit parasitic environment. By satisfying conditions of equal amplitude and a 180° phase difference at specific frequencies, a high-order hybrid network is equivalently reconstructed, generating four transmission zeros (TZs). A compact sixth-order LTCC filter was fabricated and tested. Measured results demonstrate a fractional bandwidth (FBW) of 38.6%, a shape factor of 1.16 (based on the 20-dB/3-dB bandwidth ratio), and a 20-dB upper stopband extending beyond $4.28f_0$. In conclusion, the rational utilization—rather than forced isolation—of inherent parasitic effects provides an effective solution for enhancing frequency selectivity and stopband performance in high-density integrated RF front-ends. Full article

In recent years, wildfires have occurred with increasing frequency. Pixel-level annotation of high-resolution remote sensing wildfire imagery is costly and labor-intensive. Therefore, there is an urgent need for a weakly supervised wildfire detection method that balances detection accuracy and annotation efficiency. To address the key limitations of existing weakly supervised approaches based on class activation maps (CAMs), including imprecise delineation of fire boundaries, insufficient utilization of cross-modal information, and limited capability in modeling temporal characteristics, this paper proposes a dual-branch multi-scale feature fusion framework for weakly supervised wildfire detection. The proposed framework consists of a multispectral branch and a shortwave infrared (SWIR) temporal branch, which are designed to capture the spatial structural information of fire regions and the temporal variation of thermal anomalies, respectively. Attention-guided feature fusion modules are introduced at each network stage to enable complementary integration of cross-modal information. In addition, a multi-scale CAM-weighted fusion strategy is designed to jointly enhance region localization accuracy and semantic discrimination capability. Experimental evaluations are conducted on a high-resolution wildfire dataset covering 29 regions and consisting of 2206 images. The results demonstrate that the proposed method achieves an IoU of 58.7% and an F1-score of 73.5%, outperforming the state-of-the-art methods by 4.6% and 3.2%, respectively. Ablation and comparative experiments further verify that the dual-branch architecture and feature fusion strategy significantly improve fire localization accuracy and effectively reduce the missed detection rate. Full article

Accurate individual tree crown (ITC) segmentation from unmanned aerial vehicle (UAV) imagery is important for fine-scale forest inventory, plantation management, and ecological monitoring. However, delineating ITCs in dense plantation environments remains difficult because crowns are strongly adjacent, canopy structures are highly homogeneous, and crown boundaries are often blurred, making it hard for existing methods to preserve both regional integrity and boundary continuity. This study proposes the Perceptual Segment-Anything Model with Multi-head Cross-Parallel Attention (Per-SAM-MCPA), a lightweight and effective framework for fine-grained ITC segmentation in dense plantation scenes. Based on a compact ResNet-50 backbone, the framework integrates perceptual target-aware representation, multi-scale detail enhancement, global contextual modeling, and semantic-boundary collaborative refinement to improve crown discrimination and structural consistency. A perceptual relation module is used to strengthen pixel-level semantic dependency modeling, and a Multi-head Cross-Parallel Attention (MCPA) mechanism is designed to capture long-range contextual interactions through orthogonally decomposed spatial attention, improving global geometric consistency with limited computational overhead. A Composite Constraint Loss (CCL) that combines a weighted cross-entropy loss, a structural similarity loss, and a boundary term based on Hausdorff distance is introduced to jointly optimize region-level segmentation quality and boundary fidelity. Experiments on the Catalpa bungei UAV dataset show that the proposed method achieves an intersection over union (IoU) of 87.3% and an F1-score of 91.0%, outperforming representative baseline methods such as SAM and Mask R-CNN while maintaining an inference speed of 35.7 FPS on a single GPU. These results indicate that Per-SAM-MCPA offers an accurate, efficient, and practical solution for ITC segmentation in dense plantation environments. Full article

Braided rivers are difficult to monitor because of unstable mainstream migration, complex planform morphology, and intense channel adjustment. To address this challenge, this study develops an integrated remote-sensing framework that links cross-sensor surface-water extraction, geometry-reliable boundary reconstruction, and river-geometry metric derivation for channel dynamics monitoring. Using the braided reach of the Lower Yellow River (LYR) as the study area, the framework was applied to investigate abnormal channel dynamics during 1986–2025. Results show that the improved deep learning model achieved robust and consistent surface-water extraction across Landsat-8, Landsat-7, and Sentinel-2 imagery, while the boundary reconstruction procedure effectively reduced raster-induced jagged artefacts and improved the geometric reliability of extracted channel boundaries. Based on the reconstructed boundaries, water-surface width, river centerline, sinuosity, and the Deviation Degree from Regulated River Alignments were derived and used to identify abnormal channel-dynamics reaches. In the braided reach of the LYR, the results revealed clear spatial concentration, temporal intermittency, and an upstream shift in abnormal-reach occurrence after 2000. Overall, the proposed framework extends remote sensing from surface-water mapping to long-term, geometry-reliable monitoring of braided-river channel dynamics and provides practical support for potentially unstable reach screening and warning-oriented river management. Full article

Farmland resources are fundamental to human survival and play a vital role in ensuring global food security. However, farmland boundary detection remains a significant technical challenge due to the low proportion of boundary pixels, multi-scale variations, and weak boundary continuity. To address these issues, this study proposes DCFENet, a dual-branch collaborative feature enhancement network. Specifically, a multi-scale feature fusion attention module TA-ASPP (Task-Aware Atrous Spatial Pyramid Pooling) is designed, which effectively enhances the network’s perception of farmland boundary features by integrating multi-scale dilated convolutions with skeleton-aware attention. In addition, a dual-branch decoding structure is proposed to enhance boundary localization and global topology modeling through boundary-aware gating and cross-branch feature fusion, thereby improving the boundary continuity. Furthermore, a collaborative constraint mechanism is proposed for dual-branch decoding, which supervises the two decoders using boundary loss and skeleton loss, thereby enhancing structural consistency and topology preservation. Experimental results demonstrate that DCFENet achieves precision, recall, and boundary IoU of 74.5%, 68.1%, and 77.4%, respectively, representing an improvement of 26.8%, 36.3%, and 13.2% compared with ResNet18_UNet. It also outperforms mainstream methods such as UNet, EdgeNAT, and EDTER. In terms of computational efficiency, DCFENet contains 26.43 M parameters and 37.43 G FLOPs, with a memory usage of 1.03 GB and an inference speed of 97.97 FPS, achieving a good balance between accuracy and efficiency. The results demonstrate the efficiency and accuracy of DCFENet in extracting farmland boundaries from high-resolution remote sensing images, providing technical support for farmland management and the advancement of precision and digital agriculture. Full article

This study numerically investigates the aerodynamic and thermal interactions between a full-scale metro train and the surrounding airflow within a confined tunnel environment using steady-state Reynolds-averaged Navier–Stokes (RANS) simulations. The six-car train, with a total length of 108 m and a cross-sectional area of 5.97 m², operates in a tunnel with a 9.83 square meter cross-section, resulting in a high blockage ratio of approximately 60 percent. The Shear Stress Transport (SST) k–ω turbulence model and a high-resolution finite-volume mesh comprising over 8.5 million elements were employed to capture detailed near-wall phenomena. Six representative motion scenarios were analyzed, including early acceleration, peak cruising, and deceleration phases, with realistic thermal boundary conditions applied by assigning the tunnel air temperature as 29.2 °C and the train surface temperature as 35.0 °C. Velocity, pressure, temperature, and turbulence kinetic energy distributions were extracted from both longitudinal and cross-sectional planes. In addition to visual contour assessments, pointwise and spatially averaged field data were examined to quantify the development of airflow structures, pressure distribution, and thermal behavior. The results reveal speed-dependent aerodynamic resistance, pronounced recirculation and stagnation zones around the train nose and tail, and variations in convective heat transfer rates that evolve with train velocity. These findings provide insights into tunnel ventilation design and thermal management for underground metro operations, representing a novel integration of full-scale computational fluid dynamics (CFD) with thermal characterization under realistic conditions. Full article

Gully type debris flows are sudden, highly destructive geological hazards requiring accurate, real-time monitoring for effective early warning. However, single-modal visual monitoring is sensitive to complex environments, while existing multi-modal fusion approaches rely on static strategies, limiting adaptability and modal complementarity. Blurred boundary segmentation, class imbalance, and real-time deployment challenges also remain unaddressed. To overcome these issues, this study proposes a cross-modal dynamic feature fusion framework integrating visible and infrared imagery, consisting of a shared backbone for multi-scale feature extraction, a dynamic feature aggregation module for adaptive heterogeneous fusion, a lightweight context-aware semantic segmentation network, and a composite loss function to enhance boundary delineation and mitigate class imbalance. Validated on a self-constructed dual-modal debris flow dataset and public benchmarks, the method achieves an mIoU of 75.6%, outperforming state-of-the-art methods by 3.1%. It meets real-time monitoring requirements and exhibits strong generalization, providing a practical solution for debris flow monitoring with great potential for disaster early warning deployment. Full article

Disaster risk reduction and management are essential for sustainable development in territories highly exposed and vulnerable to natural hazards. Recent disasters in the Canary Islands have highlighted the importance of proactive preparedness and systemic approaches to risk management, emphasizing the need to better understand existing barriers to disaster risk reduction (DRR). This study develops an analysis of risk governance within the current planning instruments in the Canary Islands, the island of Tenerife, and the municipality of Candelaria. The research examines the integration of DRR across strategic, territorial, urban, and emergency planning at the regional, insular, and municipal levels. The findings identify key challenges and opportunities for integrating DRR within existing planning frameworks, highlighting both the potential and the limitations of current instruments as cross-cutting tools for building more resilient territories. While Tenerife has a relatively solid administrative and planning structure that could support a more systemic vision of risk, sectoral fragmentation and coordination gaps remain. Overall, the study contributes to the ongoing discussion on advancing risk governance from a systemic perspective at the local level. The challenges identified delineate the boundaries and directions for improvement, offering a valuable contribution to the existing body of knowledge. Full article

Millimeter-wave radar imaging plays an increasingly important role in autonomous driving road perception due to its robustness under adverse weather conditions. However, radar images are inherently contaminated by multiplicative speckle noise, which severely degrades structural continuity, weakens target boundaries, and limits the perception of road scenes and surrounding objects. To address this problem, this paper proposes a structural-prior deep learning network for millimeter-wave radar image enhancement. The proposed framework first introduces an adaptive Otsu-based masking strategy to extract salient scattering structures and generate a coarse image structural prior for subsequent restoration. Guided by this prior, the network performs progressive feature enhancement through a continuous attention mechanism that integrates residual channel attention, context-aware feature extraction, and convolutional block attention, thereby enabling effective multi-scale representation learning while suppressing signal-dependent speckle interference. In addition, a composite loss function is designed by combining logarithmic denoising gain, total variation regularization, and a $\beta$-index edge-preservation term to jointly improve noise suppression, spatial smoothness, and structural fidelity. The proposed method is evaluated on the synthetic UC Merced dataset under different noise intensities and via cross-domain inference on the real-world RADIATE millimeter-wave radar dataset for autonomous driving scenarios. Experimental results demonstrate that the proposed network consistently outperforms conventional filtering methods and representative deep learning baselines in terms of PSNR, SSIM, $\beta$-index, and ENL while providing a superior preservation of road structures, target contours, and scene geometry. Ablation studies further confirm the effectiveness of the structural-prior guidance and continuous attention design. Furthermore, the network achieves a rapid inference latency of 12.35 milliseconds. These results indicate that the proposed method provides an effective and robust solution for millimeter-wave radar image enhancement and offers practical value for downstream road-scene perception in autonomous driving environments. Full article