Prediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks

TL;DR

This study employs LSTM neural networks to forecast monthly temperature and rainfall in Bangladesh using 115 years of historical data, aiming to improve understanding of weather patterns and seasonal disease outbreaks.

Contribution

The paper introduces an LSTM-based model for long-term weather prediction in Bangladesh, addressing a gap in neural network applications for regional climate analysis.

Findings

LSTM achieved a mean temperature prediction error of -0.38°C.

Rainfall prediction error was -17.64mm.

The model aids in understanding weather pattern changes and disease outbreak risks.

Abstract

Temperature and rainfall have a significant impact on economic growth as well as the outbreak of seasonal diseases in a region. In spite of that inadequate studies have been carried out for analyzing the weather pattern of Bangladesh implementing the artificial neural network. Therefore, in this study, we are implementing a Long Short-term Memory (LSTM) model to forecast the month-wise temperature and rainfall by analyzing 115 years (1901-2015) of weather data of Bangladesh. The LSTM model has shown a mean error of -0.38oC in case of predicting the month-wise temperature for 2 years and -17.64mm in case of predicting the rainfall. This prediction model can help to understand the weather pattern changes as well as studying seasonal diseases of Bangladesh whose outbreaks are dependent on regional temperature and/or rainfall.