Open AccessEffects of Learning Rates and Optimization Algorithms on Forecasting Accuracy of Hourly Typhoon Rainfall: Experiments With Convolutional Neural Network
Author(s) -
Uddin Md. Jalal,
Li Yubin,
Sattar Md. Abdus,
Nasrin Zahan Most.,
Lu Chunsong
Publication year - 2022
Publication title -
earth and space science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.843
H-Index - 23
ISSN - 2333-5084
DOI - 10.1029/2021ea002168
Subject(s) - typhoon , convolutional neural network , artificial intelligence , artificial neural network , computer science , machine learning , moment (physics) , mean squared error , gradient descent , algorithm , meteorology , statistics , mathematics , geography , physics , classical mechanics
The current study used seven optimization algorithms such as stochastic gradient descent (SGD), root mean square propagation (RMSprop), adaptive grad (AdaGrad), adaptive delta (AdaDelta), adaptive moment estimation (Adam), adaptive maximum (Adamax), and Nesterov‐accelerated adaptive moment estimation (Nadam) and eight learning rates (1, 0.1, 0.01, 0.001, 0.0001, le‐05, le‐06, and le‐07) to investigate the effects of these learning rates and optimizers on the forecasting performance of the convolutional neural network (CNN) model to forecast hourly typhoon rainfall. The model was developed using antecedent hourly typhoon rainfall within a 500 km radius from each typhoon center. Results showed that too‐large and too‐small learning rates would result in the inability of the model to learn anything to forecast hourly typhoon rainfall. The CNN model showed the best performance for learning rates of 0.1, 0.01, and 0.001 to forecast hourly typhoon rainfall. For long‐lead‐time forecasting (1–6 hr), the CNN model with SGD, RMSprop, AdaGrad, AdaDelta, Adam, Adamax, Nadam optimizers and learning rates of 0.1, 0.01, and 0.001 showed more accurate forecasts than the existing models. Therefore, this study recommends that future work may consider the CNN model as an alternative to the existing model for disaster warning systems.