| 26 Jan 2026
The first 25-year, quarterly 10-m land change map of China's Loess Plateau reveals long-term and substantial soil erosion mitigation
Abstract. Unsustainable human activities have driven global ecological degradation. In China, decades of restoration policies have been implemented to reverse this trend in severely degraded regions with catastrophic soil erosion, transforming them into landscapes of ecological recovery. However, the evolution of soil erosion in these regions remains poorly quantified due to the absence of high-resolution, long-term, and high-frequency monitoring data. Here, to address this gap and provide a reliable spatiotemporal benchmark dataset, we conducted the first 10-m quarterly wall-to-wall land change mapping for China's flagship ecological restoration site: the Loess Plateau, based on the developed cross-temporal consistency-constraint deep learning framework. The dataset was generated using over 10 terabytes of Sentinel and Landsat imagery and documents land-cover dynamics across 100 quarterly time steps from 2000 to 2024, showing an overall accuracy of 81.44 % based on 40,000 annotated samples and 79.8 % for third-party validation sources. The resulting maps record pronounced land-cover dynamics, including forest expansion (+13,131 km2), cropland expansion (+28,095 km2), and bare land reduction (-65,029 km2) over the past decades. Furthermore, the produced dataset was combined with environmental factors to measure the 25-year quarter-level soil erosion, where comparison with government survey data shows strong consistency, with a mean absolute error of 4.50 %. The dataset further illustrates that long-term ecological interventions have substantially reduced erosion intensity in the region by 30 % over the past 25 years, from 13.34 to 9.35 t/(hm2·a). Based on this benchmark, the long-term, fine-grained soil erosion becomes possible to estimate. The data-driven analysis indicates that current erosion is most severe in the central and southwestern Loess Plateau, and scenario modeling based on multiple factors suggests that optimized vegetation distribution – including grassland expansion and cropland-to-forest conversion – could potentially reduce future erosion intensity to 6.42 t/(hm2·a). This dataset provides a comprehensive benchmark for erosion mitigation in the Loess Plateau and its underlying drivers, providing critical insights for sustainable land management, ecological restoration, and policy development both in China and across fragile ecosystems worldwide. The land-cover maps and soil erosion maps is available at
https://www.scidb.cn/en/s/ZJFB3u (Cheng et al., 2025).
This manuscript presents a substantial advancement in both methodology and data availability for investigating soil erosion dynamics in fragile ecosystems, with a particular focus on the Loess Plateau. By integrating long-term time-series Landsat and Sentinel imagery with relevant environmental datasets, the authors develop a high-resolution land-cover and soil erosion dataset spanning 25 years, while further shortening the update frequency to a quarterly scale. Such temporal coverage and resolution represent a notable improvement over existing regional product. The reported mapping performance is robust for a large-scale application, with an overall accuracy of 81.44% for land-cover classification and a mean absolute error of 4.5% for soil erosion estimates. Based on an examination of the released dataset, this work is expected to provide a valuable data foundation for future studies on land-surface processes, ecological restoration, and environmental change across the Loess Plateau. Leveraging this self-produced dataset, the authors further analyze the spatial and temporal evolution of land cover and soil erosion, revealing a pronounced overall reduction in erosion intensity over the study period. The long-term and high-frequency observations enable novel insights into the seasonal heterogeneity of erosion driven by precipitation, the role of vegetation dynamics in erosion mitigation, and the influence of topographic factors. In addition, the attempt to assess potential erosion under an optimized vegetation configuration provides practical implications for soil conservation and land management strategies in the region.
The manuscript is clearly written and accompanied by high-quality data visualizations. Overall, this study makes a valuable contribution in terms of both data products and analytical perspectives, and I believe it is suitable for publication after revisions. The detailed comments are as follows: