Prediction Of Temperature And Rainfall In Bangladesh Using Long Short Term Memory Recurrent Neural Networks
Mohammad Mahmudur Rahman Khan, Md. Abu Bakr Siddique, Shadman Sakib, Anas Aziz, Ihtyaz Kader Tasawar, Ziad Hossain
Abstract
Temperature and rainfall have a significant impact on the 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 Shortterm Memory (LSTM) model to forecast the monthwise temperature and rainfall by analyzing 115 years (1901-2015) of weather data of Bangladesh. The LSTM model has showed a mean error of -0.38°C in case of predicting the monthwise 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.