Li et al. (2026) A two-layer intelligent decision-making framework for optimizing irrigation and fertilization scheduling in irrigated farmland systems

Identification

• Journal: Computers and Electronics in Agriculture
• Year: 2026
• Date: 2026-04-02
• Authors: Yue Li, Min Hu, Zhijun Chen, Yufei Han, Dongyang Ren, Xu Xu, Yunwu Xiong, Quanzhong Huang, Guanhua Huang
• DOI: 10.1016/j.compag.2026.111721

Research Groups

• State Key Laboratory of Efficient Utilization of Agricultural Water Resources, Beijing, China
• Observation and Research Station for Efficient Utilization of Water Research in Hetao Irrigation District of Inner Mongolia, Ministry of Water Resources, China
• Center for Agricultural Water Research in China, China Agricultural University, Beijing, China
• Chinese-Israeli International Center for Research and Training in Agriculture, China Agricultural University, Beijing, China

Short Summary

This study developed a two-layer AI-based framework to optimize irrigation and nitrogen fertilization timing in irrigated farmlands, demonstrating significant improvements in agricultural productivity, economic benefits, and sustainability indicators while reducing pollution and global warming potential compared to traditional practices.

Objective

• To develop an intelligent decision-making framework that efficiently and stably balances agronomic, economic, environmental, and climatic indicators to optimize irrigation and nitrogen fertilization times (INFT) in irrigated farmland systems.

Study Configuration

• Spatial Scale: Wheat and maize farmlands in the Hetao Irrigation District of Northwest China.
• Temporal Scale: Across 48 scenarios combining irrigation and nitrogen application times, evaluated for wet, normal, and dry hydrological years.

Methodology and Data

• Models used: A two-layer intelligent decision-making framework based on an AI platform, coupling an agro-hydrological model (AHC) with three multi-criteria decision-making (MCDM) methods (VIKOR, TOPSIS, and AHP). A sustainability index (SUSI) was used for final evaluation.
• Data sources: Simulated scenarios combining irrigation and nitrogen application times under different hydrological years, applied to wheat and maize farmlands.

Main Results

• The optimal irrigation and nitrogen fertilization times (INFT) achieved improvements of 3.7–39.2% in yield, economic benefits (EB), irrigation water productivity (IWP), and partial factor productivity of nitrogen (PFPn) compared to local traditional practices.
• Significant reductions were observed in nitrogen pollution load (NPL) by 20.8–51.2% and global warming potential (GWP) by 3.1–9.6%.
• The sustainability index (SUSI) of wheat and maize farmland systems increased by 28.5–106.9% relative to local control scenarios across wet, normal, and dry hydrological years.
• The AI-based decision-making framework reduced the time required for a full decision cycle to 6–9% of that needed by traditional approaches.

Contributions

• Development of a novel two-layer intelligent decision-making framework leveraging an AI platform for optimizing irrigation and nitrogen fertilization scheduling.
• Integration of an agro-hydrological model with multi-criteria decision-making methods and a sustainability index to balance diverse agricultural indicators.
• Demonstration of substantial improvements in agricultural productivity, economic benefits, and environmental sustainability (reduced pollution and global warming potential) compared to traditional management.
• Significant reduction in decision-making time and automation of complex agricultural management processes through the AI platform.
• Provides a feasible pathway for formulating efficient and sustainable irrigation-fertilization strategies and highlights the potential of AI in complex agricultural systems.

Funding

Not specified in the provided text.

Citation

@article{Li2026twolayer,
  author = {Li, Yue and Hu, Min and Chen, Zhijun and Han, Yufei and Ren, Dongyang and Xu, Xu and Xiong, Yunwu and Huang, Quanzhong and Huang, Guanhua},
  title = {A two-layer intelligent decision-making framework for optimizing irrigation and fertilization scheduling in irrigated farmland systems},
  journal = {Computers and Electronics in Agriculture},
  year = {2026},
  doi = {10.1016/j.compag.2026.111721},
  url = {https://doi.org/10.1016/j.compag.2026.111721}
}