Improving the green efficiency of urban land use (GEULU) is essential for optimizing resource utilization while minimizing waste and pollution, making it a critical factor influencing the sustainability of urban development. However, the spatiotemporal heterogeneity of the impact of China’s New-Style Urbanization (NU) policy on the GEULU, particularly at the urban agglomeration scale, remains understudied. This study employed a super SBM-DDF-GML model and spatial data analysis to examine the characteristics and spatiotemporal dynamics of the GEULU and its interactions with varying implementations of NU at the regional, urban agglomeration, and city levels. The results show that China’s GEULU followed a “U-shaped” tendency from 2006 to 2020. Cities in western China exhibit higher levels of green efficiency but slower growth, compared with lower absolute levels and faster development rates amongst the eastern cities. The GEULU displays a significant positive spatial autocorrelation, with “high-high clusters” shifting from west to east and “low-low clusters” moving in the opposite direction. The impact of NU on the GEULU is divergent: positive in eastern and central regions but negative in the western areas. Economic urbanization, urban population growth, and the clustering of research and education facilitate green efficiency, while urban sprawl significantly hinders its improvement. Social urbanization and digitalization exert adverse effects on green efficiency across many cities. Ecological and environmental protections promote the GEULU in southwestern cities but obstruct it in northeastern cities. The negative effect of NU on the green efficiency has diminished over time, while its positive effects have grown stronger. These findings provide insightful information for urban planners and politicians in crafting region-contextualized adaptive strategies to enhance sustainable urbanization and efficient land use in China.

Developing an effective vegetation classification method for mountain–plain transition zones is critical for understanding ecological patterns, evaluating ecosystem services, and guiding conservation efforts. Existing methods perform well in mountainous and plain areas but lack verification in mountain–plain transition zones. This study utilized terrain data and Sentinel-1 and Sentinel-2 imagery to extract topographic, spectral, texture, and SAR features as well as the vegetation index. By combining feature sets and applying feature elimination algorithms, the classification performance of one-dimensional convolutional neural networks (1D-CNNs), Random Forest (RF), and Multilayer Perceptron (MLP) was evaluated to determine the optimal feature combinations and methods. The results show the following: (1) multi-feature combinations, especially spectral and topographic features, significantly improved classification accuracy; (2) Recursive Feature Elimination based on Random Forest (RF-RFE) outperformed ReliefF in feature selection, identifying more representative features; (3) all three algorithms performed well, with consistent spatial results. The MLP algorithm achieved the best overall accuracy (OA: 81.65%, Kappa: 77.75%), demonstrating robustness and lower dependence on feature quantity. This study presents an efficient and robust vegetation classification workflow, verifies its applicability in mountain–plain transition zones, and provides valuable insights for small-region vegetation classification under similar topographic conditions globally.