A New Multi-objective Approach to Optimize Irrigation Using a Crop Simulation Model and Weather History
Optimization of water consumption in agriculture is necessary to preserve freshwater reserves and reduce the environment’s burden. Finding optimal irrigation and water resources for crops is necessary to increase the efficiency of water usage. Many optimization approaches maximize crop yield or profit but do not consider the impact on the environment. We propose a machine learning approach based on the crop simulation model WOFOST to assess the crop yield and water use efficiency. In our research, we use weather history to evaluate various weather scenarios. The application of multi-criteria optimization based on the non-dominated sorting genetic algorithm-II (NSGA-II) allows users to find the dates and volume of water for irrigation, maximizing the yield and reducing the total water consumption. In the study case, we compared the effectiveness of NSGA-II with Monte Carlo search and a real farmer’s strategy. We showed a decrease in water consumption simultaneously with increased sugar-beet yield using the NSGA-II algorithm. Our approach yielded a higher potato crop than a farmer with a similar level of water consumption. The NSGA-II algorithm received an increase in yield for potato crops, but water use efficiency remained at the farmer’s level. NSGA-II used water resources more efficiently than the Monte Carlo search and reduced water losses to the lower soil horizons.
PDF Abstract
Colab
