A GA-Based BP Artificial Neural Network for Estimating Monthly Surface Air Temperature of the Antarctic during 1960–2019

Figure 3

Flowchart of BPANN optimized with GA. The parameters in GA mainly include population size, evolutionary times, crossover probability, and mutation probability. In this study, the parameters were set as follows: population size of 100, evolutionary times of 50, crossover probability of 0.4, and mutation probability of 0.1. In this study, the GA-BPANN model was constructed with the build-in BP and GA functions in MATLAB (2016a) GA and ANN toolbox.