Implementation of LSTM (Long Short Term Memory) Algorithm to Predict Weather in Central Java

Abstract

Agro-indutrial agricultural production such as red onions in Indonesia has a very important share in driving Indonesia's economic growth, especially in Central Java province which contributed 28.15% of the total national red onion production in 2021. Weather conditions have a major influence on the red onion planting process until the red onions are ready to be harvested. In this study, the objective is to predict various types of weather such as rainfall, air temperature, and air humidity in seven districts in Central Java, namely Brebes, Temanggung, Demak, Boyolali, Kendal, Pati, and Tegal. To do this, the use of the LSTM (Long Short Term Memory) algorithm with its ability to store memory longer than RNN will be reliable for predicting various types of weather in the future. This research was developed with the CRISP-DM (Cross Industry Process Model for Data Mining) method which has a goal-oriented approach, this method is a mature and widely accepted method in Data Mining with various applications in Machine Learning. With the final results from 39 models by using the evaluation of the average value of train MSE 0.013, test RMSE 0.11, test MSE of 0.02, test RMSE 0.12 and succeed to predict 5 days or months ahead from the last data that is provided.