The complexity of urban street vitality is reflected in the interaction of multiple factors. A deep understanding of the multi-dimensional driving mechanisms behind it is crucial to enhancing urban street vitality. However, existing studies lack comprehensive interpretative analyses of urban multi-source data, making it difficult to uncover these drivers’ nonlinear relationships and interaction effects fully. This study introduces an interpretable machine learning framework, using Nanchang, China as a case study. It utilizes urban multi-source data to explore how these variables influence different dimensions of street vitality. This study’s innovation lies in employing an integrated measurement approach which reveals the complex nonlinearities and interaction effects between data, providing a more comprehensive explanation. The results not only demonstrate the strong explanatory power of the measurement approach but also reveal that (1) built environment indicators play a key role in influencing street vitality, showing significant spatial positive correlations; (2) different dimensions of street vitality exhibit nonlinear characteristics, with transit station density being the most influential one; and (3) cluster analysis revealed distinct built environment and socioeconomic characteristics across various street vitality types. This study provides urban planners with a data-driven quantitative tool to help formulate more effective strategies for enhancing street vitality.

Intensified human activities and changes in land-use patterns have led to numerous eco-environmental challenges. A comprehensive understanding of the eco-environmental effects of land-use transitions and their driving mechanisms is essential for developing scientifically sound and sustainable environmental management strategies. However, existing studies often lack a comprehensive analysis of these mechanisms due to methodological limitations. This study investigates the eco-environmental effects of land-use transitions in the Poyang Lake Region over the past 30 years from the perspective of the production-living-ecological space (PLES) framework. Additionally, a geographically explainable artificial intelligence (GeoXAI) framework is introduced to further explore the mechanisms underlying these eco-environmental effects. The GeoXAI framework effectively addresses the challenges of integrating nonlinear relationships and spatial effects, which are often not adequately captured by traditional models. The results indicate that (1) the conversion of agricultural space to forest and lake spaces is the primary factor contributing to eco-environmental improvement. Conversely, the occupation of forest and lake spaces by agricultural and residential uses constitutes the main driver of eco-environmental degradation. (2) The GeoXAI demonstrated excellent performance by incorporating geographic variables to address the absence of spatial causality in traditional machine learning. (3) High-altitude and protected water areas are more sensitive to human activities. In contrast, geographic factors have a greater impact on densely populated urban areas. The results and methodology presented here can serve as a reference for eco-environmental assessment and decision-making in other areas facing similar land-use transformation challenges.

Traditional villages are of great importance for understanding human–environment interactions. However, with the advancement of urbanization, the gradual disappearance of spatial characteristics and the homogenization of landscapes have emerged as prominent issues. Existing studies primarily adopt a single-disciplinary perspective to analyze villages spatial morphology and its influencing factors, relying heavily on qualitative analysis methods. These efforts are often constrained by the lack of digital infrastructure and insufficient data. To address the current research limitations, this paper proposes a Hierarchical Graph Neural Network (HGNN) model that integrates multi-source data to conduct an in-depth analysis of villages' spatial morphology. The framework includes two types of nodes—input nodes and communication nodes—and two types of edges—static input edges and dynamic communication edges. By combining Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT), the proposed model efficiently integrates multimodal features under a two-stage feature update mechanism. Additionally, based on existing principles for classifying villages spatial morphology, the paper introduces a relational pooling mechanism and implements a joint training strategy across 17 subtypes. Experimental results demonstrate that this method achieves significant performance improvements over existing approaches in multimodal fusion and classification tasks. Additionally, the proposed joint optimization of all sub-types lifts mean accuracy/F1 from 0.71 / 0.83 (independent models) to 0.82 / 0.90, driven by a 6% gain for parcel tasks. Our method provides scientific evidence for exploring villages' spatial patterns and generative logic.