Chen et al. (2026) Spatial and Temporal characteristics and driving force analysis of vegetation cover change in Shanxi Province, China based on kNDVI and XGBoost-SHAP model

Identification

• Journal: Frontiers in Environmental Science
• Year: 2026
• Date: 2026-09-17
• Authors: Jie Chen, Yi Hou, Jianhua Xue, Jianhua Ni, Hao Liu, Pengxiang Gao
• DOI: 10.3389/fenvs.2026.1948848

Research Groups

• School of Architecture and Surveying Engineering, Shanxi Datong University, China
• School of Coal Engineering, Shanxi Datong University, China
• School of Resources and Environmental Engineering, Anhui University, China

Short Summary

This study investigates the spatiotemporal evolution of vegetation coverage in Shanxi Province, China, using kernel Normalized Difference Vegetation Index (kNDVI) datasets and an XGBoost-SHAP machine learning framework. The results show a significant increase in kNDVI values over the past 25 years, with a predicted persistence of this trend.

Objective

• Investigate the spatiotemporal evolution of vegetation coverage in Shanxi Province, China.
• Identify the dominant natural and anthropogenic drivers governing vegetation dynamics.
• Quantify the independent contributions and nonlinear marginal responses of driving factors.

Study Configuration

• Spatial Scale: Provincial scale (Shanxi Province, China)
• Temporal Scale: 25 years (2000-2024)

Methodology and Data

• Models used: XGBoost-SHAP machine learning framework
• Data sources: MOD13Q1 remote sensing products, multi-source meteorological, topographic, and socioeconomic datasets

Main Results

• kNDVI values show a significant increase over the past 25 years.
• The major axis of vegetation spatial distribution maintains a stable northeast-southwest orientation.
• The standard deviational ellipse exhibits moderate outward expansion, and the vegetation gravity center shows a general northwestward shift.

Contributions

• This study provides a comprehensive understanding of the spatiotemporal evolution of vegetation coverage in Shanxi Province, China.
• The results can inform ecological restoration planning and territorial spatial governance in the region.

Funding

• National Natural Science Foundation of China (Grant No. 42177002)
• Key Research and Development Program of Shanxi Province (Grant No. 202103R0504001)

Citation

@article{Chen2026Spatial,
  author = {Chen, Jie and Hou, Yi and Xue, Jianhua and Ni, Jianhua and Liu, Hao and Gao, Pengxiang},
  title = {Spatial and Temporal characteristics and driving force analysis of vegetation cover change in Shanxi Province, China based on kNDVI and XGBoost-SHAP model},
  journal = {Frontiers in Environmental Science},
  year = {2026},
  doi = {10.3389/fenvs.2026.1948848},
  url = {https://doi.org/10.3389/fenvs.2026.1948848}
}