Weather Forecasting Using Artificial Neural Network (ANN): A Review

Abstract

Extreme weather occurrences provide issues that necessitate the development of technology capable of accurate analysis and exact prediction in order to successfully reduce their effects. Artificial neural networks (ANNs) have appeared in the last few years as a promising weather forecasting technology because of their capacity to manage intricate and nonlinear weather factors. The use of ANNs in weather element prediction has shown considerable improvements in forecasting precision and accuracy. Factors influencing an ANN model's efficacy include input Data Type and Volume for Training, Hidden Layer Neuron Count, network architecture, Activation Functions, and training algorithms. In this paper, we will present a thorough review of the applications of Artificial Neural Networks (ANNs) in weather forecasting, specifically focusing on temperature and rainfall prediction over the past 15 years. To enhance reader comprehension, The work of numerous researchers in this topic is methodically analyzed and compared in in tabular format. The authors aim to facilitate future research decisions by offering an organized review, aiding in the determination of suitable input features, transfer functions, and training algorithms for accurate temperature and rainfall predictions.