Li et al. (2026) Rice Cropping Pattern Mapping Using GEE-Based Sentinel-1/2 Time-Series Imagery and Machine Learning

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-24
• Authors: Xuan Li, Lintao Chen, Lin Chen, Chao Su, Hoi Leong Lee, Ruci Wang, Xuguang Tang
• DOI: 10.3390/rs18193302

Research Groups

• Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences
• Google Earth Engine Team

Short Summary

This study presents a high-precision mapping framework for major rice cropping patterns in the Yangtze River Delta region, China, using multi-source remote sensing data on the Google Earth Engine platform. The framework achieved an overall accuracy of 93.8% and demonstrated effective classification of three predominant cropping systems.

Objective

• To develop a high-precision mapping framework for major rice cropping patterns in the Yangtze River Delta region, China

Study Configuration

• Spatial Scale: Regional (Yangtze River Delta)
• Temporal Scale: Annual (2024–2025 growing season)

Methodology and Data

• Models used: Gradient Boosting Tree (GBTREE), Random Forest (RF), Support Vector Machine (SVM)
• Data sources: Sentinel-1 radar backscatter, Sentinel-2 optical indices (NDVI, LSWI), topographic factors (DEM, slope)

Main Results

• The GBTREE classifier achieved the highest overall accuracy (93.8%), Kappa coefficient (0.87), and macro-average F1 score (88.3%) in this specific experiment.
• Multi-temporal NDVI phenological features were the primary drivers of classification accuracy.
• Radar backscatter and water indices provided essential complementary information, while topographic factors served as spatial constraints at the regional scale.

Contributions

• This study demonstrates the effectiveness of integrating multi-source remote sensing data on the GEE platform with the GBTREE classifier for high-precision mapping of rice cropping patterns in complex agricultural landscapes.
• The approach provides a reliable technical foundation for regional agricultural structure analysis, crop rotation assessment, and sustainable agricultural monitoring.

Funding

• National Natural Science Foundation of China (Grant No. 42171355)
• Chinese Academy of Sciences Strategic Pilot Project (Grant No. XDA19040401)

Citation

@article{Li2026Rice,
  author = {Li, Xuan and Chen, Lintao and Chen, Lin and Su, Chao and Lee, Hoi Leong and Wang, Ruci and Tang, Xuguang},
  title = {Rice Cropping Pattern Mapping Using GEE-Based Sentinel-1/2 Time-Series Imagery and Machine Learning},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18193302},
  url = {https://doi.org/10.3390/rs18193302}
}