Abstract: To improve the accuracy of crop water requirement prediction, a model based on Least Square Support Vector Machine (LS-SVM) optimized by Particle Swarm Optimization (PSO) is put forward. Relative humidity, air temperature,  solar radiation and wind speed are considered as input variables. A nonnegative linear combination of polynomial kernel function and radial basis kernel function is used as the kernel function of LS-SVM. PSO and cross validation are applied to optimize the parameters of LS-SVM. Experimental results indicate that LS-SVM optimized by PSO outperforms neural network and random forest. It can be used for water-saving irrigation, and has good application value.

Key words: crop water requirements, support vector machine, particle swarm optimization, kernel function