任泽岭 et al. (2026) Quantifying crop yield responses to irrigation deficits using aquacrop and XGBoost-SHAP: Insights from the Ningxia irrigation district

Identification

• Journal: Agricultural Water Management
• Year: 2026
• Date: 2026-07-07
• Authors: 任泽岭, Binquan Li, J Liu, Y ZHAO, 李况, Yongnan Zhu, Huanghao Yu
• DOI: 10.1016/j.agwat.2026.110621

Research Groups

• State Key Laboratory of Water Cycle and Water Security, Hohai University, Nanjing 210098, China
• College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China
• Key Laboratory of Hydrologic-Cycle and Hydrodynamic-System of Ministry of Water Resources, Hohai University, Nanjing 210098, China
• State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China

Short Summary

This study uses a coupled crop mechanistic modeling and explainable machine learning framework to quantify the nonlinear yield responses of spring wheat, spring maize, and rice to irrigation deficits in the Ningxia Irrigation District. The results indicate that spring wheat and rice exhibit strong nonlinear relationships between irrigation deficit and yield loss, while spring maize displays a near-linear response.

Objective

• Investigate the nonlinear crop yield responses to irrigation deficits using a mechanistic modeling approach.
• Quantify the relative importance of monthly irrigation during the growth periods for each crop.

Study Configuration

• Spatial Scale: Regional scale (Ningxia Irrigation District)
• Temporal Scale: Annual and seasonal scales

Methodology and Data

• Models used: AquaCrop model, XGBoost machine learning algorithm
• Data sources: Local yield observations, growth period days, meteorological data from 1960 to 2019, soil properties, crop yields, planting areas, and planting structures for spring wheat, spring maize, and rice

Main Results

• Spring wheat and rice exhibit strong nonlinear relationships between irrigation deficit and yield loss.
• Spring maize displays a near-linear response within the explored range.
• The Gompertz curve is suitable for capturing crop yield responses to water stress induced by irrigation deficits.

Contributions

• This study provides valuable insights for tailoring deficit irrigation strategies based on crop-specific drought tolerance zones.
• The coupled mechanistic modeling and machine learning framework can be applied to other regions with similar climate and agricultural conditions.

Funding

• This research was supported by the National Natural Science Foundation of China (Grant No. 51879219), the Key Research and Development Program of Jiangsu Province (Grant No. BE2019071601), and the Fundamental Research Funds for the Central Universities (Grant No. B21001).

Citation

@article{任泽岭2026Quantifying,
  author = {任泽岭 and Li, Binquan and Liu, J and ZHAO, Y and 李况 and Zhu, Yongnan and Yu, Huanghao},
  title = {Quantifying crop yield responses to irrigation deficits using aquacrop and XGBoost-SHAP: Insights from the Ningxia irrigation district},
  journal = {Agricultural Water Management},
  year = {2026},
  doi = {10.1016/j.agwat.2026.110621},
  url = {https://doi.org/10.1016/j.agwat.2026.110621}
}