Humidity Prediction Model using Long Short Term Memory in Recurrent Neural Network

Abstract

Based on the importance of estimating air humidity in a region, this study proposes a method for air humidity prediction, based on deep learning using the Long Short Term Memory (LSTM) method. The results showed that LSTM, which is a variant of Recurrent Neural Network (RNN), can be used to predict air humidity better than other methods. The data training process by using the linear regression produced the MSE value of 0.417 and the RMSE value of 0.646, whereas the LSTM method produced the MSE value of 0.018 and the RMSE value of 0.136.