Automatic Multi-Temporal Land Cover Mapping with Medium Spatial Resolution Using the Model Migration Method

Accurate land cover mapping plays a critical role in enhancing our understanding of Earth’s energy balance, carbon cycle, and ecosystem dynamics. However, existing methods for producing multi-epoch land cover products still heavily depend on manual intervention, limiting their efficiency and scalability. This study introduces an automated approach for multi-epoch land cover mapping using remote sensing imagery and the model migration strategy. Landsat ETM+ and OLI images with a 30 m resolution were utilized as the primary data sources. An automatic training sample extraction method based on prior multi-source land cover products was first utilized. Then, based on the generated training dataset and a random forest classifier, local adaptive land cover classification models of the reference year were developed. Finally, by migrating the classification model to the target epoch, multi-epoch land cover products were generated. Yuli County in Xinjiang and Linxi County in Inner Mongolia were used as test cases. The classification models were first generated in 2020 and then migrated to 2010 to test the effectiveness of automated land cover classification over multiple years. Our mapping results show high accuracy in both regions, with Yuli County achieving 92.52% in 2020 and 88.33% in 2010, and Linxi County achieving 90.28% in 2020 and 85.28% in 2010. These results demonstrate the reliability of our proposed automated land cover mapping strategy. Additionally, the uncertainty analysis of the model migration strategy indicated that land cover types such as water bodies, wetlands, and impervious surfaces, which exhibit significant spectral changes over time, were the least suitable for model migration. Our results can offer valuable insights for medium-resolution, multi-epoch land cover mapping, which could facilitate more efficient and accurate environmental assessments.