Optimize the irrigation and fertilizer schedules by combining DSSAT and genetic algorithm.

Area of Science:

• Agricultural Science
• Computational Science

Background:

• Maize yield is critical for global food security.
• Optimizing irrigation and fertilizer schedules is a key research area.
• Traditional methods rely on field experiments or crop models, with limited integration of optimization algorithms.

Purpose of the Study:

• To combine the genetic algorithm (GA) with the DSSAT crop model.
• To optimize irrigation and fertilizer schedules for maize in China.
• To provide a theoretical basis for improved maize cultivation practices.

Main Methods:

• Calibrated and verified the DSSAT crop model using field experimental data.
• Integrated the genetic algorithm (GA) with the DSSAT crop model.
• Ran simulations to obtain optimized irrigation and fertilizer schedules.

Main Results:

• The calibrated DSSAT model showed good simulation accuracy with RMSE ranging from 0.262 to 0.580 Mg/ha.
• The optimized schedules resulted in a yield increase of 1.9%–2.6%.
• Economic benefits improved by 7.3%–8.9% compared to previous methods.

Conclusions:

• The combined GA-DSSAT approach demonstrates significant optimization effects for maize cultivation.
• This integrated method offers a promising strategy for enhancing crop yield and economic returns.
• The methodology has broad research prospects for optimizing agricultural management practices.