Unpacking the black box of deep learning for identifying El Niño-Southern oscillation

Yu Xue Sun, Yusupjan Habibulla, Gaoke Hu, Jun Meng, Zhenghui Lu, Maoxin Liu, Xiaosong Chen

Communications in Theoretical Physics · 26 June 2023

In one sentence. CNN recognizes El Nino and La Nina phases with 86.4% validation accuracy, and weight analysis identifies the few active kernels driving the classification.

Abstract

Abstract By training a convolutional neural network (CNN) model, we successfully recognize different phases of the El Niño-Southern oscillation. Our model achieves high recognition performance, with accuracy rates of 89.4% for the training dataset and 86.4% for the validation dataset. Through statistical analysis of the weight parameter distribution and activation output in the CNN, we find that most of the convolution kernels and hidden layer neurons remain inactive, while only two convolution kernels and two hidden layer neurons play active roles. By examining the weight parameters of connections between the active convolution kernels and the active hidden neurons, we can automatically differentiate various types of El Niño and La Niña, thereby identifying the specific functions of each part of the CNN. We anticipate that this progress will be helpful for future studies on both climate prediction and a deeper understanding of artificial neural networks.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.