Using deep learning to predict the East Asian summer monsoon

• Published in: Environmental research letters Vol. 16; no. 12; pp. 124006 - 124015
• Main Authors: Tang, Yuheng, Duan, Anmin
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.12.2021
• Subjects: Artificial neural networks; Confidence intervals; Correlation coefficient; Correlation coefficients; Deep learning; Dynamic models; East Asian summer monsoon; heat map; machine learning; Monsoons; Neural networks; Predictions; Regression models; Robustness (mathematics); Statistical analysis; Summer; Transfer learning
• ISSN: 1748-9326; 1748-9326
• DOI: 10.1088/1748-9326/ac34bc

Abstract Accurate prediction of the East Asian summer monsoon (EASM) is beneficial to billions of people’s production and lives. Here, a convolutional neural network (CNN) and transfer learning are used to predict the EASM. The results of the constructed CNN regression model show that the prediction of the CNN regression model is highly consistent with the reanalysis dataset, with a correlation coefficient of 0.78, which is higher than that of each of the current state-of-the-art dynamic models. The heat map method indicates that the robust precursor signals in the CNN regression model agree well with previous theoretical studies and can provide the quantitative contribution of different signals for EASM prediction. The CNN regression model can predict the EASM one year ahead with a confidence level above 95%. The above method can not only improve the prediction of the EASM but also help to identify the involved physical predictors.