Building change detection is an important task in the remote sensing field, and the powerful feature extraction ability of the deep neural network model shows strong advantages in this task. However, the datasets used for this study are mostly three-band high-resolution remote sensing images from a single data source, and few spectral features limit the development of building change detection from multisource remote sensing images. To investigate the influence of spectral and texture features on the effect of building change detection based on deep learning, a multisource building change detection dataset (MS-HS BCD dataset) is produced in this paper using GF-1 high-resolution remote sensing images and Sentinel-2B multispectral remote sensing images. According to the different resolutions of each Sentinel-2B band, eight different multisource spectral data combinations are designed, and six advanced network models are selected for the experiments. After adding multisource spectral and texture feature data, the results show that the detection effects of the six networks improve to different degrees. Taking the MSF-Net network as an example, the F1-score and IOU improved by 0.67% and 1.09%, respectively, compared with high-resolution images, and by 7.57% and 6.21% compared with multispectral images.

Precise monitoring and extraction of coastal aquaculture ponds are crucial for ecological conservation and the sustainable use of coastal wetlands. However, traditional image analysis techniques often struggle to efficiently extract aquaculture ponds in the complex, heterogeneous environments of coastal wetlands. While deep learning approaches have enhanced automation, existing models are limited by their reliance on single-feature attention, which fails to capture the global structural characteristics of aquaculture ponds, such as boundaries and internal spatial relationships, thus restricting their generalization capability. To address these issues, this paper introduces a novel Multi-task Aquaculture pond Extraction Network (MAENet). This network facilitates the supervised extraction process by modeling pond boundaries and the distances from internal points to these boundaries. It notably enhances performance in complex environments and significantly boosts generalization capabilities by learning global structural features. Firstly, a shared encoder-decoder architecture was constructed, leveraging large kernel depthwise separable convolution and residual optimization, thereby enhancing both local and global feature representations. Then, a selective task fusion module was developed to optimize the allocation of shared feature space, effectively alleviating the negative transfer problem of multi-task architecture. Finally, the adoption of an adaptively optimized multi-task loss function obviates the necessity for manual allocation of weights. Ablation and comparative experiments using GF2 imagery from the Qingdao coastal wetlands show that MAENet outperforms existing methods in complex scenarios. Furthermore, transfer experiments with JL1 imagery from the Jiangmen and Yantai demonstrate the strong generalization capability of the proposed method across different environments.

This study introduces a hierarchical dual-model detection framework for accurately monitoring spotted seals (Phoca largha) in the Liaohe River estuary by using deep learning on Unmanned Aerial Vehicles (UAVs). To address challenges such as weak target features, background interference and limited edge computing capacity, this study deploys an optimized FF-YOLOv10 lightweight model on UAVs for rapid target localization, followed by an enhanced PP-YOLOv7 model on ground stations for precise detection. The FF-YOLOv10 model reduces computational complexity by 24.2% and increases inference speed by 33.3%, while the PP-YOLOv7 model achieves 94.2% precision with a 1.9% increase in recall rate. This framework provides an efficient and precise technical solution for the long-term ecological monitoring of marine endangered species, supporting habitat conservation policy formulation and ecosystem health assessments.

Current passive microwave satellites like SMAP still face limitations in observational frequency and responsiveness in regions with frequent cloud cover, dense vegetation, or complex terrain, making it difficult to achieve continuous global monitoring with high spatio-temporal resolution. To enhance global high-frequency monitoring capabilities, this study utilizes global reflectivity data provided by the Tianmu-1 (TM-1) constellation since 2023, combined with multiple auxiliary variables, including NDVI, VWC, precipitation, and elevation, to develop a 9 km resolution soil moisture retrieval model. Several spatial clustering and temporal partitioning strategies are incorporated for systematic evaluation. Additionally, since the publicly available TM-1 L1 reflectivity data does not provide separable polarization channels, this study uses DDM/specular point reflectivity as the primary observable quantity for modeling and mitigates non-soil factor interference by introducing multi-source priors such as NDVI, VWC, precipitation, terrain, and roughness. Unlike SMAP’s “single orbit daily fixed local time” observation mode, TM-1, leveraging multi-constellation and multi-orbit reflection geometry, offers more balanced temporal sampling and availability in cloudy, rainy, and mid-to-high latitude regions. This enables temporal gap filling and rapid event response (such as moisture transitions within hours after precipitation events) during periods of SMAP’s quality masking or intermittent data loss. Results indicate that the model combining LC-cluster with seasonal partitioning delivers the best performance at the cluster level, achieving a correlation coefficient (R) of 0.8155 and an unbiased RMSE (ubRMSE) of 0.0689 cm³/cm³, with a particularly strong performance in barren and shrub ecosystems. Comparisons with SMAP and ISMN datasets show that TM-1 is consistent with mainstream products in trend tracking and systematic error control, providing valuable support for global and high-latitude studies of dynamic hydrothermal processes due to its more balanced mid- and high-latitude orbital coverage.

Conventional infrastructure appraisal in Africa prioritizes short-term economic performance while insufficiently accounting for the environmental conditions that govern long-term sustainability, spatial equity, and development resilience. To address this gap, this study develops an explicitly SDG-oriented spatial–ecological framework to examine how environmental quality conditions the economic returns of large-scale infrastructure investments under corridor-based development. The primary objective is to quantify infrastructure–environment complementarity and identify ecological thresholds regulating spatial spillovers and investment effectiveness along Tanzania’s Belt and Road Initiative (BRI) corridors. High-resolution remote sensing and spatially explicit socioeconomic data for 2012–2023 are integrated within a spatial econometric design. A Spatial Durbin Model (SDM) incorporating the Normalized Difference Vegetation Index (NDVI) is estimated to capture non-linear interaction effects, with economic activity proxied by Night-Time Light (NTL) intensity across 2680 corridor grid cells. The results identify a statistically robust ecological threshold at NDVI = −0.8σ, beyond which infrastructure investments shift from low to high economic effectiveness. A strong positive infrastructure–environment interaction (β = 6.44, p < 0.001) indicates that environmental quality functions as a productive modulating factor rather than a passive constraint. Spatial classification shows that 63% of corridor areas are investment-ready, while 15% require ecological restoration prior to effective infrastructure deployment. Although institutional quality and long-term post-construction dynamics are not explicitly modeled, the framework provides a replicable and policy-relevant decision-support tool, offering actionable guidance for aligning corridor development with SDGs 9, 11, and 13 and advancing sustainable infrastructure planning in the Global South.

Tunnel point cloud semantic segmentation is a critical step in achieving refined perception and intelligent management of tunnel structures. Addressing common challenges including indistinct boundaries and fine-grained category discrimination, this paper proposes MFPNet, a multi-scale feature perception network specifically designed for tunnel scenarios. This approach employs kernel convolution to effectively model local point cloud geometries within continuous spaces. Building upon this foundation, an error-feedback-based local-global feature fusion mechanism is designed. Through bidirectional information exchange, higher-level semantic information compensates for and constrains lower-level geometric features, thereby mitigating information fragmentation across semantic hierarchies. Furthermore, an adaptive feature re-calibration and cross-scale contextual correlation mechanism is introduced to dynamically modulate multi-scale feature responses. This explicitly models contextual dependencies across scales, enabling collaborative aggregation and discriminative enhancement of multi-scale semantic information. Experimental results on tunnel point cloud datasets demonstrate that the proposed MFPNet has achieved significant improvements in both overall segmentation accuracy and category balance, with mIoU reaching 87.5%, which is 5.1% to 33.0% higher than mainstream methods such as PointNet++ and RandLA-Net, and the overall classification accuracy reaching 96.3%. These results validate the method’s efficacy in achieving high-precision three-dimensional semantic understanding within complex tunnel environments, providing robust technical support for tunnel digital twin and intelligent detection applications.