Analysis and Prediction of Rainfall with Oceanic Nino Index and Climate Variables Using Correlation Coefficient and Deep Learning

This article presents the relationship between the Oceanic Nino Index (ONI) and monthly rainfall on the southern and eastern coast of Thailand, specifically in Narathiwat, Pattani, and Yala provinces, where influences have been commonly observed. This research aims to study the relationship between the Oceanic Nino Index (ONI) and monthly rainfall to develop a model for predicting monthly rainfall. Despite previous related research, there has been no in-depth study on the relationship between the Oceanic Nino Index (ONI) and monthly rainfall in areas adjacent to the sea. The correlation coefficient was used to determine the relationship, revealing that the ONI value is significantly correlated with the amount of rainfall in the current month and the following month. This correlation paved the way for developing a model to predict monthly rainfall. Multiple linear regression, recurrent neural networks, and long short-term memory models were employed for this purpose. The study found that utilizing a recurrent neural network yielded the best prediction efficiency, with Mean Absolute Error (MAE) values of ۱۱۲.۷۶ mm for Narathiwat province, ۸۱.۰۶ mm for Pattani province, and ۹۷.۶۷ mm for Yala province. Doi: ۱۰.۲۸۹۹۱/CEJ-۲۰۲۴-۰۱۰-۰۵-۰۱ Full Text: PDF

Keywords:

Rainfall Prediction , Oceanic Nino Index , Eastern Sea Coast , Deep Learning.