Predicting pollution load at the soil-water interface is key to controlling runoff pollution in disturbed mining sites [1]. With the large-scale exploitation and smelting of ore, the solid resource and its waste (ore, waste ore, tailing sand, waste residue, etc.) result in the formation of heavy metal pollution flow in the soil-water interface under the effect of rainfall runoff [2-4]. In the long term, it could cause an increasingly prominent problem of heavy metal complex pollution in the manganese mine and the surrounding area [5]. This is particularly true for mining sites in the Hunan region of China, where largescale exploitation of metal manganese has generated large areas of degraded land. The soil and water assessment tool (SWAT) model developed by the U.S. Department of Agriculture in 1994 is a continuous distributed watershed environment model based on GIS software [6-7]. It has been widely applied to evaluate agricultural non-point source pollution [8-9]. The SWAT model includes two main parts: land surface process and water surface/confluence process. The former considers 8 modules of hydrology, meteorology, silt, soil temperature, crop growth, nutrient, pesticide, and agricultural management for system contribution; the later completes hydrological circulation and material migration of the basin through