Simulation Optimization of Water Usage and Crop Yield Using Precision Irrigation

Sustainable agriculture maximizes crop production with minimal use of resources, such as water and energy. Subsurface water retention technology (SWRT) uses an impermeable membrane in the soil to hold more water for plants. Optimal production of crops requires not only the optimal irrigation rate but also optimal shapes and placements of SWRT. Furthermore, some uncertain factors, e.g. incoming solar energy, plant transpiration rate temperature, climatic conditions, and genetics of crops are also important in crop production, thereby making the optimization process complicated. In this paper, we propose a computationally fast approach that utilizes HYDRUS-2D software for water flow simulation and DSSAT crop simulation software with an evolutionary multi-objective optimization (EMO) procedure in a coordinated manner to minimize water utilization and maximize crop production. Our method simulates SWRT in HYDRUS-2D software and calibrates and validates DSSAT model parameters according to the HYDRUS-2D simulation. Then it finds the best irrigation schedules to produce maximum crop production and water use efficiency by DSSAT. Our results show that HYDRUS-DSSAT calibration produces less than 5% validation error and the optimization procedure introduces 99% water use efficiency with the help of rainfall water and as much as 6 times increase of corn production compared to a non-optimized, random irrigation schedule without any SWRT membrane.

[1]  Gerrit Hoogenboom,et al.  Simulating water content, crop yield and nitrate-N loss under free and controlled tile drainage with subsurface irrigation using the DSSAT model , 2011 .

[2]  Kalyanmoy Deb,et al.  High dimensional model representation for solving expensive multi-objective optimization problems , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[3]  Kalyanmoy Deb,et al.  A Taxonomy for Metamodeling Frameworks for Evolutionary Multiobjective Optimization , 2019, IEEE Transactions on Evolutionary Computation.

[4]  Kalyanmoy Deb,et al.  An Efficient Nondominated Sorting Algorithm for Large Number of Fronts , 2019, IEEE Transactions on Cybernetics.

[5]  Andrey K. Guber,et al.  Subsurface Water Retention Technology Improves Root Zone Water Storage for Corn Production on Coarse‐Textured Soils , 2015 .

[6]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[7]  Kalyanmoy Deb,et al.  Metamodeling for multimodal selection functions in evolutionary multi-objective optimization , 2017, GECCO.

[8]  Kalyanmoy Deb,et al.  An integrated approach involving EMO and HYDRUS-2D software for SWRT-based precision irrigation , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[9]  Kalyanmoy Deb,et al.  Best Order Sort: A New Algorithm to Non-dominated Sorting for Evolutionary Multi-objective Optimization , 2016, GECCO.

[10]  Gary Feng,et al.  Evaluating the impact of groundwater on cotton growth and root zone water balance using Hydrus-1D coupled with a crop growth model , 2015 .

[11]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[12]  John Doe,et al.  Vadose Zone Journal 2014 Summary of Editorial Reports , 2015 .

[13]  Andrey K. Guber,et al.  Estimating nitrogen leaching losses after compost application in furrow irrigated soils of Pakistan using HYDRUS-2D software , 2016 .

[14]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[15]  Van Genuchten,et al.  A closed-form equation for predicting the hydraulic conductivity of unsaturated soils , 1980 .

[16]  James W. Jones,et al.  Decision support system for agrotechnology transfer: DSSAT v3 , 1998 .