The rapid and disordered expansion of artificial marine aquaculture areas has caused severe ecological and environmental problems. Accurate monitoring of offshore aquaculture areas is urgent and significant in order to support the scientific and sustainable management and protection of coastal marine resources. Artificial intelligence provides a valuable tool to improve marine resource monitoring. Deep learning methods have been widely used for marine object detection, but You Only Look Once (YOLO) models have not been employed for offshore aquaculture area monitoring. This study therefore evaluated the capacity of two well-known YOLO models, YOLOv5 and YOLOv7, to detect offshore aquaculture areas based on different high-resolution optical remote sensing imagery. Compared with YOLOv7 based on a satellite dataset, YOLOv5 increased the Precision value by approximately 3.29% (to 95.33%), Recall value by 3.02% (to 93.02%), mAP_0.5 by 2.03% (to 96.22%), and F1 score by 2.65% (to 94.16%). Based on the Google Earth dataset, YOLOv5 and YOLOv7 showed similar results. We found that the spatial resolution could affect the deep learning models’ performances. We used the Real-ESRGAN method to enhance the spatial resolution of satellite dataset and investigated whether super-resolution (SR) methods improved the detection accuracy of the YOLO models. The results indicated that despite improving the image clarity and resolution, the SR methods negatively affected the performance of the YOLO models for offshore aquaculture object detection. This suggests that attention should be paid to the use of SR methods before the application of deep learning models for object detection using remote sensing imagery.

The Xixia Imperial Tombs (XITs) represent a crucial, yet still largely mysterious, component of the Tangut civilization’s legacy. Located in northwestern China, this extensive necropolis offers invaluable insights into the Tangut state, culture, and burial practices. This study employs an integrated approach utilizing multi-resolution and multi-temporal satellite remote sensing data, including Gaofen-2 (GF-2), Landsat-8 OLI, declassified GAMBIT imagery, and Google Earth, combined with deep learning techniques, to conduct a comprehensive archaeological investigation of the XITs’ burial landscape. We performed geomorphological analysis of the surrounding environment and automated identification and mapping of burial mounds and mausoleum features using YOLOv5, complemented by manual interpretation of very-high-resolution (VHR) satellite imagery. Spectral indices and image fusion techniques were applied to enhance the detection of archaeological features. Our findings demonstrated the efficacy of this combined methodology for archaeology prospect, providing valuable insights into the spatial layout, geomantic considerations, and preservation status of the XITs. Notably, the analysis of declassified GAMBIT imagery facilitated the identification of a suspected true location for the ninth imperial tomb (M9), a significant contribution to understanding Xixia history through remote sensing archaeology. This research provides a replicable framework for the detection and preservation of archaeological sites using readily available satellite data, underscoring the power of advanced remote sensing and machine learning in heritage studies.

Digital Elevation Models (DEMs) constitute a core data source for Archeological Predictive Modeling. However, how quality differences among multi-source DEM propagate through complex models and subsequently affect predictive accuracy and geographic interpretation remains insufficiently understood. This study aims to develop an integrated evaluation framework that combines machine learning with SHAP-based interpretability analysis to systematically compare the suitability of mainstream open access DEM products for archeological site prediction. The results indicate that (1) in terms of vertical accuracy, Copernicus DEM and TanDEM-X achieved the best performance, with RMSE values of 2.19 m and 2.31 m, respectively, whereas ASTER exhibited the lowest accuracy (RMSE = 6.44 m) and exaggerated terrain. (2) Regarding model performance, Copernicus DEM-driven models demonstrated the highest robustness, achieving an AUC of 0.966 under the XGBoost algorithm. (3) Interpretability analysis revealed that different DEM products significantly reallocate the importance of key variables such as slope and the Topographic Wetness Index, potentially distorting scientific interpretations of ancient military defensive site-selection patterns. Copernicus DEM is recommended as a priority data source. Moreover, while pursuing higher spatial resolution, equal attention must be paid to vertical accuracy and consistency with geomorphological logic.

Accurate building contour extraction is critical for urban modeling but remains challenging due to limitations in single-source point clouds. LiDAR data suffers from sparsity and sensitivity to surface reflectance, while photogrammetric point clouds exhibit noise under occlusion and lighting variations. To overcome these constraints, we propose an end-to-end framework combining multimodal 3D fusion and deep geometric co-optimization. First, LiDAR and photogrammetric point clouds are fused through ICP registration, avoiding 2D-3D misalignment. Building points are then segmented using PointNet++. A novel Z-axis threshold projection is applied during projection, eliminating rooftop interference by constraining projections to structural walls. Initial contours extracted via Alpha-shapes undergo adaptive regularization: 1) Douglas-Peucker simplification, 2) angle-constrained vector optimization rectifying non-orthogonal corners. Validated on Ming and Qing heritage structures, our method achieves 3.7% area error (vs. 17.8% for CloudCompare) and 2.6% perimeter error. This represents the first unified pipeline combining 3D-3D data fusion with deep learning and geometric regularization, offering a promising approach for automated building modeling in complex urban and heritage environments.

Long-term monitoring of land cover dynamics is essential for evaluating conservation outcomes in World Heritage sites, yet remains challenging in conflict-affected regions with limited field observations. This study aims to reconstruct annual land cover dynamics and assess forest sustainability in the Okapi Wildlife Reserve (OWR), a World Heritage site in the Democratic Republic of Congo. Using Landsat dense time series observations (2000–2023), the Continuous Change Detection and Classification (CCDC) algorithm, landscape metrics, and the Sustainable Development Goal (SDG) 15.1.1 indicator, we developed an annual scale framework to quantify land cover changes and conservation status. The results showed that forest loss was the dominant land cover change process, with degradation accelerating after 2013. Forest disturbances were spatially heterogeneous, mainly concentrated in the boundary buffer zone and along National Road No. 4, while localized disturbances also occurred within the core protected area. Landscape fragmentation increased during the study period, and SDG 15.1.1 trends revealed differentiated conservation pressures among management zones. This study provides an annual-scale land cover history of the OWR and demonstrates the potential of Earth observation for monitoring endangered World Heritage sites.

The virtual reassembly of fragmented cultural relics remains a challenging task due to incomplete contours, complex fracture geometries, and the lack of reliable accuracy evaluation when ground-truth models are unavailable. To address these issues, this study proposes an automated virtual reassembly framework based on multi-feature extraction and hierarchical fragment matching. First, contour points are extracted from fragment point clouds using neighborhood roughness analysis and further refined through a Cylinder Box-based completion strategy to recover missing contour segments. Then, multiple complementary features, including Fast Point Feature Histograms (FPFHs), Heat Kernel Signatures (HKSs), and a spatial cube-based contour shape descriptor, are jointly constructed to characterize both local geometric details and global structural properties of fragments. To improve matching efficiency and robustness, a tree-based fragment retrieval strategy combined with a coarse-to-fine registration scheme is employed to identify adjacent fragments while reducing computational complexity. In addition, a pseudo-ground-truth accuracy evaluation method is introduced to quantitatively assess cumulative reassembly errors in the absence of reliable reference data. Experiments conducted on the public Buddha head dataset demonstrate that the proposed method achieves stable and visually consistent reassembly results, with a cumulative error as low as 1.58%, while significantly reducing retrieval computations compared with exhaustive matching strategies. These results indicate that the proposed framework provides a practical and verifiable solution for the automated digital restoration of fragmented cultural relics.