Convolutional Neural Network- ANN- E (Tanh): A New Deep Learning Model for Predicting Rainfall

• Published in: Water resources management Vol. 37; no. 4; pp. 1785 - 1810
• Main Authors: Afshari Nia, Mahdie, Panahi, Fatemeh, Ehteram, Mohammad
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.03.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial neural networks; Atmospheric Sciences; Chiroptera; Civil Engineering; Deep learning; Drought; Earth and Environmental Science; Earth Sciences; Environment; Error functions; Flood predictions; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Hydrology/Water Resources; Iran; Machine learning; Neural networks; Optimization; Precipitation; prediction; rain; Rainfall; Training level; water; Iran; Hydrological predictions; Optimization algorithm; Hybrid model; New activation function; Water resource management
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-023-03454-8

The prediction of rainfall is essential for monitoring droughts and floods. The purpose of this paper is to develop a deep learning model for predicting monthly rainfall. The new model is used to predict rainfall in the Kashan plain of Iran. This study combines a deep learning model with an artificial neural network (ANN) model to predict rainfall. In this study, a convolutional neural network (CONV) is used as a deep learning model. The paper also introduces a new activation function called E-Tanh to develop ANN models. The new model has two main advantages. The model automatically determines key features. In addition, the new activation function can enhance the precision of ANN models. Lagged rainfall values are inserted into the models to predict rainfall. This study uses a bat optimization algorithm to choose inputs. At the training level, the mean absolute percentage errors (MAPES) of CONV-ANN-ANN-E-Tanh, CONV, and ANN-E-Tanh were 0.5%, 1%, and 2%, respectively. At the testing level, the MAPEs of CONV-ANN -E-Tanh, CONV, and ANN-E-Tanh were 1%, 3%, and 4%, respectively. The E-Tanh performed better than other activation functions based on error function values. Also, the CONV-ANN-E-Tanh can reduce CPU time. Our results show that the new hybrid model is a reliable tool for simulating complex phenomena.