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

Figure 2

The structure of the BPANN model. The number of neurons of each layer is denoted as n, p, and m, respectively. (i = 1, 2, …, n and j = 1, 2, …, p) represents the weights between the input and hidden layer, while (j = 1, 2, …, p and k = 1, 2, …, m) represents the weights between the hidden and the output layer. The threshold values of the hidden layer and the output layer are and , respectively. f (·) is an activation function by which the mapping process from the input layer to the hidden layer is implemented and (·) is an activation function by which the mapping process from the hidden layer to the output layer is implemented. In this study, the default activation functions of the BPANN model in the MATLAB (2016a) ANN toolbox were adopted. The parameters in the BPANN mainly include the maximum training times, learning rate, and training target accuracy. The parameters of the BPANN model in this study include a maximum training time of 2000, a learning rate of 0.5, and a training target accuracy of 0.001.