Calculating the Coefficients in the Jensen Model Using the Tuna Swarm Optimization Algorithm

Abstract

【Objective】 The Jensen formula is a nonlinear model for calculating the response of crop yield to water and nutrient applications. It contains a number of parameters which need calibration against experimental data. The aim of this paper is to present a method to inversely estimate these parameters using experimental data. 【Method】 The method is based on the tuna swarm optimization algorithm (TSO). A distribution estimation (ITSO) was used to form the tuna swarm optimization algorithm (TSO), and the performance of the proposed tuna swarm optimization algorithm was verified against other algorithms based on the CEC2017 test. The accuracy and efficiency of the method were compared with other methods based on experimental data obtained from the Xiaohe Irrigation Experimental Station in Shanxi province. 【Result】 Comparing the performance of ITSO, TSO, GWO, WOA, SSA and BOA methods shows that the proposed algorithm is the best. Comparing ITSO with the nonlinear regression analysis in the SPSS software and TSO shows that the relative error of the proposed method is 7.79%, 8.13% and 7.79%, respectively. The TSO algorithm converged in 50 iterations, while the ITSO algorithm found the optimal solution in just 35 iterations. 【Conclusion】 The tuna swarm optimization algorithm combined with the distribution estimation (ITSO) is efficient for estimating the parameters in the Jensen model. It is highly accurate and converges fast.

Keywords

• crop water production function
• jensen model
• model parameter solution
• distribution estimation
• tuna swarm optimization algorithm