Prediction of biological and grain yield of barley using multiple regression and artificial neural network models

Abstract

Prediction of barley yield is an attempt to accurately forecast the outcome of a specific situation, using as input information extracted from a set of data features that potentially describe the situation. In this study, an attempt has been made to analyze and compare multiple linear regression (MLR), and artificial neural network (ANN) including multi-layer perceptron (MLP) and radial basis function (RBF) models to predicting biological yield (BY) and yield (Y) of barely. Data was collected from the literatures on the subject of barley production that was existed in http://sid.ir website. A total of 10563 data from 17 features were prepared in Excel software sheets. Then, the Matlab software was used to compare the models. Results of MLR model based on R2 showed that Model 7, with 1000-kernel weight (gr), OC (%), grain/spike, soil pH, N applied (kg/ha), plant height (cm), and irrigation regime (according to FC) and Model 8 with 1000-kernel weight (gr), OC (%), soil pH, grain/spike, HI (%), plant height (cm), irrigation regime (according to FC), and plant density (plant/m2), were the best models for prediction BY and Y of barley, respectively. The highest standardized coefficient (β) for prediction of BY was obtained in 1000-kernel weight (0.621), OC (0.396) and grain/spike (0.385). Also, for prediction of Y, 1000-kernel weight, OC, and grain/spike with 0.547, 0.403, and 0.347 had the highest β, respectively. Among the MLR, MLP and RBF models, MLP model had the highest R2 values for prediction of BY (R2=0.894) and Y (R2=0.922). Overall, ANN models can be used to successfully estimate BY and Y from data.