Assessing the spatio-temporal variability and driving forces of soil erosion on the Loess Plateau is critical for ecological and environmental management. In this paper, the Revised Universal Soil Loss Equation (RUSLE) model, the patch-generating land use simulation, and the Geographical Detector are used to investigate the spatio-temporal variations of the Loess Plateau’s soil erosion from 2000 to 2050. The results showed that: (1) The primary categories of soil erosion from 2000 to 2020 were moderate, mild, and slight, and the average level of soil erosion exhibited a decreasing and then an increasing tendency during the last 20 years. (2) Soil erosion was directly impacted by changes in land use, with cropland and forest being the primary land use and land cover changes in the study region. Cropland and construction land being turned into woodland between 2000 and 2020 resulted in a significant decrease in the severity of soil erosion. Projected soil erosion is expected to increase significantly between 2020 and 2050 due to arable land being converted into construction land. (3) The key variables impacting the spatial distribution of soil erosion were LUCC (Land-Use and Land-Cover Change), NDVI (Normalized Difference Vegetation Index), and slope, and the interplay of these variables may increase their ability to explain soil erosion. Grasslands with an NDVI ranging from 0.9 to 1, rain ranging from 0.805 to 0.854 m, a slope above 35°, and a terrain elevation ranging from 1595 to 2559 m were identified as having a high risk of soil erosion. Soil erosion prevention and management efforts should focus on the ecological restoration of upland areas in the future.

The preservation and enhancement of ecosystem services are essential for maintaining ecological balance and sustainable growth. The Heihe River Basin (HRB) is important for ecological security in Northwest China, yet is a fragile ecological environment. Understanding the dynamics and evolution of ESs is vital for balancing resource exploitation, socioeconomic development, and ecological protection. Using the InVEST model, we calculated water yield, habitat quality, and carbon stock in the HRB during 2000–2020 and examined shifts in ecosystem services. Trade-offs and synergies among ESs were assessed using GeoDa and key drivers were identified through the geodetector model. The spatial distribution of water yield, habitat quality, and carbon storage varied significantly, with high values concentrated in the upstream Qilian Mountains and low values in the downstream desert areas. High carbon storage clusters were stable, high water yield clusters increased and subsequently decreased, and high habitat quality clusters fluctuated. Carbon storage, water yield, and habitat quality exhibited a synergistic relationship. Climate and topography, particularly vapor emissions and elevation, were the primary factors influencing ESs, while socioeconomic factors had a lesser impact. These findings provide valuable insights for sustainable ecosystem management and conservation in the HRB and other arid inland watershed regions.