Abstract: In order to investigate the effects of land use change on ecosystem service value (ESV) in Guangxi Autonomous Region, the random forest algorithm was used to classify the land use of the 5 periods of Landsat series remote sensing images from 2000 to 2020, the land use dynamic degree and land use transfer matrix methods were used to reveal the land use change patterns, the ecosystem services value was calculated by using the equivalence factor method, with its spatiotemporal variation characteristics explored, and the intrinsic link between each land use type and changes in ecosystem service values was analyzed. The results showed that forest land and arable land were the main land use types in Guangxi, and the area of construction land had been increasing year by year, mainly by encroaching on arable land. The dynamic degree of single land use type was in the order of unutilized land > grassland > construction land > cropland > water > forest land. The overall ESV in Guangxi showed a fluctuating downward trend. The value of unidirectional ecosystem services was dominated by hydrological regulation and climate regulation. In terms of spatial distribution, the ESV was characterized by a low spatial distribution in the middle and high spatial distribution in the surrounding area. For the changes of ESV in Guangxi in the last 20 years, grassland, forest land and cropland were the main contributing factors and sensitive factors.