Depicting the spatiotemporal dynamics of vegetation cover in the Yellow River Basin (YRB) and delineating the influences of climate change and human activities on the dynamics have been of significant importance for understanding the surface earth systems in general and also for formulating ecological protection plans of the YRB in particular. This study uses the GIMMS NDVI dataset from 1982 to 2015 and the MOD13A1 NDVI dataset from 2000 to 2021 to explore the spatial and temporal characteristics of vegetation cover in the YRB for the period from 1982 to 2021 with an attempt to reveal the influencing factors. The spatial distribution and temporal variation characteristics of vegetation cover are analyzed by maximum value composite, Theil-Sen median trend analysis, and Mann–Kendall test. Combined with the mean annual temperature and annual precipitation in the same period, influencing factors of vegetation cover in the YRB are discussed by using binary linear regression analysis and residual analysis. Results show that: (1) the multi-year average NDVI values increase from the northwest to the southeast and that the annual mean values of the vegetation covers fluctuate relatively greatly along an increasing trend with a growth rate of 0.019/(10a). Understandably, the monthly mean NDVI values show a single-peak distribution pattern, with August being the peak time (0.4936). (2) 77.35% of the studied areas are characterized by exhibiting an increasing trend of vegetation cover during the study period (i.e., 1982–2021). (3) Vegetation cover of the YRB is affected by the combined effects of climate change and human activities, with human activities being more significant in the observed amelioration of vegetation cover.

Individualization of buildings is one of the key issues in the establishment of three-dimensional (3D) building models. Most existing individualization methods rely on inefficient manual separation, while deep learning approaches require extensive pre-training and are highly influenced by the spatial structure of the models. To address these issues, this paper proposes a novel method for 3D building individualization that integrates SAMPolyBuild with multiple spatial-geometric features. Leveraging the zero-shot learning capability of SAMPolyBuild, the method first performs coarse extraction of individual buildings, then refines the extraction accuracy using multiple spatial-geometric features. Innovatively, two statistical parameters—Jensen-Shannon Divergence and Earth Mover’s Distance—are introduced into the building identification process. To validate the feasibility and effectiveness of the proposed method, experiments were conducted on the Semantic Urban Meshes (SUM) dataset. The results demonstrate that the method can effectively extract individual building models from urban oblique photogrammetric 3D models, achieving an F1-score of approximately 0.83 for buildings with typical spatial structures.

Jinlu Zhang, Yi Cheng, Wen Ge, Shuxue Li, Ge Zhu, Lianshuai Cao. Episodes -0001;0:. https://doi.org/10.18814/epiiugs/2025/025027

I. Large-scale oblique photogrammetry point clouds are crucial in urban 3D modelling and smart city applications (Chew et al. 2022; Li and Zhou 2024; Singh and Yadav 2024). However, these point clo...