Chen et al. (2025) An NSGA-II-XGBoost Machine Learning Approach for High-Precision Cropland Identification in Highland Areas: A Case Study of Xundian County, Yunnan, China

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

Identification

• Journal: Remote Sensing
• Year: 2025
• Date: 2025-12-25
• Authors: Guoping Chen, Z. Wang, Side Gui, Junsan Zhao, Yandong Wang, Lei Li
• DOI: 10.3390/rs18010081

Research Groups

Not explicitly stated in the provided text.

Short Summary

This study developed a high-precision cropland identification model for plateau and mountainous regions, demonstrating that an NSGA-II optimized XGBoost model achieved superior performance with an overall accuracy of 95.75% in Xundian County, Yunnan Province.

Objective

• To develop a high-precision cropland identification model tailored to plateau and mountainous environments to advance precision agriculture and support the scientific planning and refined management of agricultural resources.

Study Configuration

• Spatial Scale: Xundian County, Yunnan Province, China (regional scale).
• Temporal Scale: Not explicitly stated for the study period, but time-series features were integrated.

Methodology and Data

• Models used: Support Vector Machine (SVM), Random Forest (RF), Tabular Multiple Prediction (TABM), XGBoost, and NSGA-II optimized XGBoost (NSGA-II-XGBoost).
• Data sources: Multispectral, Synthetic Aperture Radar (SAR), topographic, texture, and time-series features. Baseline land use map generated by fusing datasets from the European Space Agency (ESA), the Environmental Systems Research Institute (ESRI), and the China Resource and Environment Data Cloud (CRLC). 4000 randomly selected sample points were used for model comparison.

Main Results

• The NSGA-II-XGBoost model consistently achieved superior performance compared to other machine learning algorithms.
• Key performance metrics for the NSGA-II-XGBoost model were:
  • Overall accuracy: 95.75%
  • Kappa coefficient: 0.91
  • Recall: 0.96
  • F1-score: 0.96
• The model demonstrated strong capability for cropland mapping under complex topographic conditions.

Contributions

• Development of a high-precision cropland identification model specifically tailored for complex plateau and mountainous regions.
• Introduction and validation of the NSGA-II-XGBoost model, demonstrating its superior performance, stability, and adaptability for cropland mapping in challenging terrains.
• Provides a robust technical framework and methodological reference for farmland protection and natural resource classification in other mountainous regions.

Funding

Not explicitly stated in the provided text.

Citation

@article{Chen2025NSGAIIXGBoost,
  author = {Chen, Guoping and Wang, Z. and Gui, Side and Zhao, Junsan and Wang, Yandong and Li, Lei},
  title = {An NSGA-II-XGBoost Machine Learning Approach for High-Precision Cropland Identification in Highland Areas: A Case Study of Xundian County, Yunnan, China},
  journal = {Remote Sensing},
  year = {2025},
  doi = {10.3390/rs18010081},
  url = {https://doi.org/10.3390/rs18010081}
}