Mapping China's Annual Tree Cover: A Holistic and Efficient Framework Integrating Satellite Imagery and Advanced Modeling

Comprehending large-scale tree cover dynamics is paramount for effective environmental management and policy formulation. This study introduces a comprehensive and cost-effective framework for mapping China's Annual Tree Cover (2000–2022) at a 30m spatial resolution. The methodology, amalgamating time-series MODIS and Landsat imagery with a global-local automated sampling approach, partitioned modeling, and random forest-based resolution-adaptive techniques, demonstrates compelling validation outcomes. Validation against Global Ecosystem Dynamics Investigation (GEDI) reference data yields an R
²
of 0.49 and an RMSE of 20.8%. Further validation using national forest inventory (NFI) data reinforces this accuracy, achieving an R
²
of 0.82 and an RMSE of 14.1%. Beyond enhancing comprehension of China's terrestrial ecosystem, the resulting tree cover dataset emerges as a pivotal resource, facilitating informed decision-making in environmental conservation and land-use planning.