Unsupervised change detection of land cover in multispectral satellite remote sensing images with a spatial resolution of 2–5 m has always been a challenging task. This paper presents a method of detecting land cover changes in high-spatial-resolution remote sensing imagery. This method has three characteristics: (1) Extended center-symmetric local binary pattern (XCS-LBP) is used to extract image features to emphasize spatial context information in initial change detection. Then, spectral information is combined to improve the accuracy of change detection. (2) The local histogram distance of XCS-LBP features is used as the change vector to improve the expression of change information. (3) A progressive Otsu method is developed for threshold segmentation of the change vector to reduce the false detection rate. Four datasets with different landscape complexities and seven state-of-the-art unsupervised change detection methods were used to test the performance of the proposed method. Quantitative results showed that the proposed method reduced the false detection rate and improved the accuracy of the detection of land cover changes. The F1 score achieved by the proposed method reached 0.8688, 0.8867, 0.7725, and 0.6634, respectively, which are higher than the highest corresponding F1 score achieved by the benchmark methods (0.8533, 0.8549, 0.6545, and 0.5895, respectively).

Context: Under global climate change and intensified human activities, the Yangtze River Basin (YZRB) and Yellow River Basin (YRB) face escalating challenges to ecosystem services (ESs), including water scarcity and biodiversity loss. Understanding ES dynamics is essential for sustainable landscape management. Objectives: This study aimed to (1) predict spatiotemporal changes in land cover and ESs from 2030 to 2100 under SSP1–2.6, SSP3–7.0, and SSP5–8.5 scenarios, and (2) quantify pixel-scale ES trade-offs/synergies and their driving factors. Methods: An integrated SSP–LUH2–PLUS–InVEST/CS framework was developed, combining climate scenarios, land use simulations, and ES assessments. The framework was applied to both basins to project future land cover changes and quantify ES responses under varying radiative forcing scenarios. Results: Forests expanded notably in the YZRB under SSP1–2.6 and SSP3–7.0, largely replacing grasslands and croplands, whereas grasslands remained in the YRB. Water yield (WY), soil conservation (SC), and habitat quality (HQ) improved the most under SSP1–2.6, whereas carbon sequestration (CS) peaked under SSP5–8.5. Synergies prevailed among WY–SC, CS–SC, and SC–HQ across all scenarios, whereas CS–HQ shifts to trade-offs under SSP5–8.5. ES interactions were scenario-dependent, with precipitation, temperature, potential evapotranspiration, land cover, and elevation as key drivers, shifting from land use-driven under low emissions to climate-driven under high emissions. Conclusions: Future ES management in the YZRB and YRB should adopt scenario-specific strategies, optimizing land use under low-emission pathways and applying climate-adaptive interventions under high-emission scenarios to sustain ES provision.