Land use change is related to a series of core issues of global environmental change, such as environmental quality improvement, sustainable utilization of resources, energy reuse and climate change. In this study, Google Earth Engine (GEE), a remote sensing natural environment monitoring and analysis platform, was used to realize the combination of Landsat TM/OLI data images with spectral features and topographic features, and the random forest machine learning classification method was used to supervise and classify the low-cloud composite image data of Ordos City. The results show that: (1) GEE has a powerful computing function, which can realize efficient and high-precision in-depth analysis of long-term multi-temporal remote sensing images and monitoring of land use change, and the accuracy of acquisition can reach 87%. Compared with other data sets in the same period, the overall and local classification results are more distinct than ESRI (Environmental Systems Research Institute) and GlobeLand 30 data products. Slightly lower than the Institute of Aerospace Information Innovation of the Chinese Academy of Sciences to obtain global 30 m of land cover fine classification products. (2) The overall accuracy of the land cover data of Ordos City from 2003 to 2023 is between 79–87%, and the Kappa coefficient is between 0.79–0.84. (3) Climate, terrain, population and other interactive factors combined with socio-economic population data and national and local policies are the main factors affecting land use change between 2003 and 2023.