Li et al. (2026) Mapping complex cropping patterns in China (2018–2021) at 10 m resolution: a data-driven framework based on multi-product integration and Google satellite embedding

Identification

• Journal: Earth system science data
• Year: 2026
• Date: 2026-07-30
• Authors: Xiyu Li, Le Yu
• DOI: 10.5194/essd-18-5601-2026

Research Groups

• Ministry of Education Key Laboratory for Earth System Modeling, Department of Earth System Science, Tsinghua University, Beijing, 100084, China
• Ecological Field Station for East Asian Migratory Birds, Beijing 100084, China
• Institute of Carbon Neutrality, Tsinghua University, Beijing, 100084, China

Short Summary

This study developed a data-driven crop mapping framework by integrating multiple existing crop products with Google Satellite Embeddings derived from the AlphaEarth foundation model. The framework effectively enhanced the spatial coherence and temporal stability, achieving an overall accuracy of 92.60% and an F1 score of 0.7584.

Objective

• Develop a data-driven crop mapping framework that integrates multiple existing crop products with Google Satellite Embeddings to achieve high accuracy and consistency in mapping complex cropping patterns across China.

Study Configuration

• Spatial Scale: 10m resolution
• Temporal Scale: Annual maps for the period 2018–2021

Methodology and Data

• Models used: Random Forest (RF) classifier trained on Google Satellite Embeddings derived from AlphaEarth foundation model v2.1
• Data sources: Multiple publicly available crop mapping products, Google Earth Engine cloud platform, ESA WorldCover (2020 and 2021), FROM-GLC10 (2017)

Main Results

• The framework effectively enhanced the spatial coherence and temporal stability of mapping results.
• Achieved an overall accuracy of 92.60% and an F1 score of 0.7584.
• Classified Confused areas, Low-consistency areas, and Unlabelled regions.

Contributions

• This study provides a robust foundation for refined agricultural management and policy decisions, while supporting climate-smart and sustainable land-use planning.
• The resulting datasets provide an integrated depiction of China's complex cropping systems, enabling consistent interannual assessments of changes in crop types, cropping sequences, and spatial patterns at 10m resolution.

Funding

• This research was funded by the Ministry of Education Key Laboratory for Earth System Modeling.

Citation

@article{Li2026Mapping,
  author = {Li, Xiyu and Yu, Le},
  title = {Mapping complex cropping patterns in China (2018–2021) at 10 m resolution: a data-driven framework based on multi-product integration and Google satellite embedding},
  journal = {Earth system science data},
  year = {2026},
  doi = {10.5194/essd-18-5601-2026},
  url = {https://doi.org/10.5194/essd-18-5601-2026}
}