Chang et al. (2026) Climate-driven redistribution of foxtail millet (Setaria italica) suitability in China revealed by biomod2 ensemble models: implications for dryland crop adaptation

Identification

• Journal: Frontiers in Plant Science
• Year: 2026
• Date: 2026-09-09
• Authors: Jiakun Yan, Xiaolin Wang, Xiong Zhang, Yuming Chang, Ke Lu
• DOI: 10.3389/fpls.2026.1882902

Research Groups

• Shaanxi Key Laboratory of Ecological Restoration in Northern Shaanxi Mining Area, China College of Advanced Agricultural Sciences, Yulin University, Yulin, China
• First Clinical Medical College, College of Information and Engineering, Wenzhou Medical University, Wenzhou, China

Short Summary

This study used biomod2 ensemble models to project the potential suitable distribution of foxtail millet (Setaria italica) in China under current and future climate scenarios. The results show that the total potential suitable area will increase by 4.77%–18.87% by the 2090s, with expansion mainly projected along the northern and peripheral margins of the current suitable region.

Objective

• To develop an ensemble species distribution modelling framework to predict the potential suitable distribution of S. italica in China under different climate scenarios.
• To evaluate the predictive performance of single algorithms and ensemble models for suitability projection.

Study Configuration

• Spatial Scale: National scale, covering the entire territory of China.
• Temporal Scale: Historical baseline (1970-2000) and future periods (2030s, 2050s, 2070s, and 2090s).

Methodology and Data

• Models used: Biomod2 ensemble species distribution modelling framework, including eight single-algorithm models: classification tree analysis (CTA), flexible discriminant analysis (FDA), generalized linear model (GLM), generalized boosting model (GBM), random forest (RF), maximum entropy (MAXENT), multivariate adaptive regression splines (MARS), and eXtreme Gradient Boosting (XGBOOST).
• Data sources: Occurrence records of S. italica in China, climatic, topographic, soil, and UV-B radiation variables.

Main Results

• The final EMwmeanByTSS ensemble model showed good discrimination ability and acceptable predictive performance.
• Annual precipitation (bio12), elevation (elev), minimum temperature of the coldest month (bio06), and UV-B seasonality (uvb2) were the dominant predictors, jointly contributing 82.82%.
• Under the historical baseline, the total potential suitable area was 4.09 ×10^6 km².
• Under future SSP scenarios, the total suitable area increased to 4.29 ×10^6 – 4.87 ×10^6 km².

Contributions

• This study provides a spatial basis for stable production-region protection, regional variety trials, germplasm conservation, and climate-adaptive dryland agricultural planning.
• The results highlight the importance of considering multiple climate scenarios and ensemble modelling approaches in crop suitability assessments.

Funding

• This research was supported by the Shaanxi Key Laboratory of Ecological Restoration in Northern Shaanxi Mining Area.

Citation

@article{Chang2026Climatedriven,
  author = {Chang, Lina and Yan, Jiakun and Wang, Xiaolin and Zhang, Xiong and Chang, Yuming and Lu, Ke},
  title = {Climate-driven redistribution of foxtail millet (Setaria italica) suitability in China revealed by biomod2 ensemble models: implications for dryland crop adaptation},
  journal = {Frontiers in Plant Science},
  year = {2026},
  doi = {10.3389/fpls.2026.1882902},
  url = {https://doi.org/10.3389/fpls.2026.1882902}
}