Li Wang

Accurate urban land cover information is essential for monitoring urbanization and environmental change, yet the complexity and heterogeneity of urban landscapes remain challenging for high-resolution remote sensing classification. This study used Google Satellite Embeddings as the core feature input, combined with ensemble learning and spatiotemporal post-processing, to generate annual 10 m land cover maps for 37 Chinese metropolises from 2017 to 2024. Results showed that the weighted ensemble model achieved an overall accuracy (OA) of 81.99%, 2.13% higher than the best individual model, while spatiotemporal post-processing further increased OA to 82.59%. Compared with existing land cover products such as FROM-GLC10, the proposed product achieved 4.20% higher OA. The ablation experiment showed that the embedding representation was the primary source of performance improvement. Under the same ensemble learning framework, Satellite Embedding features outperformed conventional remote sensing features by 6.54% in OA. SHapley Additive exPlanations (SHAP) analysis identified A16, A36, A51, A61, and A22 as the key embedding dimensions, while Pearson correlation analysis further revealed associations between the key dimensions and spectral, radar, texture, and topographic information. Change analysis indicated concurrent urban expansion, ecological recovery, and agricultural land contraction from 2017 to 2024, with cropland-to-forest and cropland-to-impervious-surface conversions being the most prominent transition pathways. Overall, Satellite Embeddings provide effective feature representations for annual land cover mapping and long-term change analysis in complex metropolitan environments.

Intensive anthropogenic activities in high-groundwater coal basins (HGCBs) have dramatically altered land use/land cover (LULC) patterns, exerting profound impacts on regional ecosystem carbon storage. In this study, conducted in the Yanzhou Coalfield, China, we developed a refined water body classification scheme that divides water bodies into natural, artificial, seasonal, and perennial types to better capture the ecological heterogeneity of water bodies within mining-induced subsidence areas, which is often overlooked in conventional assessments. By coupling the PLUS and InVEST models, we quantified carbon storage dynamics driven by LULC changes from 2005 to 2020 and projected carbon storage levels for 2035 under four scenarios: historical trend (HT), food security (FS), ecological restoration (ER), and coordinated development (CD). The primary findings of this study are as follows: (1) Significant differences in carbon density existed among water body types, in the order natural water bodies > seasonal water bodies > perennial water bodies > artificial water bodies. Neglecting these differences can introduce systematic biases in carbon storage assessment. (2) Cropland area decreased substantially from 2005 to 2020, while built-up land and water bodies expanded continuously. (3) Intensive LULC transitions resulted in a 12.77% decline in total carbon storage (equivalent to 2.38 × 10⁵ Mg), primarily driven by the conversion of high-carbon-density cropland to built-up land and subsidence water bodies due to coal mining activities. (4) Projections for 2035 indicate that total carbon storage would decline by an additional 11.67% under the HT scenario. In contrast, the FS, ER, and CD scenarios effectively mitigated losses, with declines of 6.15%, 5.05%, and 3.13%, respectively. The CD scenario achieved the best performance through synergistic optimization of carbon sequestration, food security, and ecological restoration objectives. These findings provide critical insights for integrating carbon sequestration objectives into land management practices in coal mining areas, thereby supporting land use optimization and climate change mitigation efforts.

Assessing ecological quality in mining areas is critical for environmental protection and sustainable resource management. However, most previous studies concentrate on large-scale analysis, overlooking fine-scale assessment in mining areas. To address this issue, this study proposed a novel analysis framework for mining areas by integrating high-resolution Landsat data, the Remote Sensing Ecological Index (RSEI), and the Random Forest regression method. Based on the framework, four decades of spatiotemporal dynamics and drivers of ecological quality were revealed in Youjiang River Valley. Results showed that from 1986 to 2024, ecological quality in Youjiang River Valley exhibited a fluctuating upward trend (slope = 0.004/year), with notable improvement concentrated in the most recent decade. Spatially, areas with a significant increasing trend in RSEI (48.71%) were mainly located in natural vegetation regions, whereas areas with a significant decreasing trend (9.11%) were concentrated in impervious surfaces and croplands in northern and central regions. Driver analysis indicates that anthropogenic factors played a crucial role in ecological quality changes. Specifically, land use intensity, precipitation, and sunshine duration were main determinants. These findings offer a comprehensive understanding of ecological quality evolution in subtropical karst mining areas and provide crucial insights for conservation and restoration efforts in Youjiang River Valley.