Rainfall Prediction in Palembang City Using the GRU and LSTM Methods

Surta, Wijaya and Tri Basuki, Kurniawan and Edi Surya, Negara and Yesi Novaria, Kunang (2023) Rainfall Prediction in Palembang City Using the GRU and LSTM Methods. Journal of Data Science, 2023 (04). pp. 1-13. ISSN 2805-5160

[img] Text
jods2023_04.pdf - Published Version
Available under License Creative Commons Attribution.

Download (581kB)
Official URL: http://ipublishing.intimal.edu.my/jods.html


Rainfall is one of the weather elements that are very important for the survival of an area. Palembang City, as one of the big cities in Indonesia, is heavily influenced by the level of rainfall that occurs every month. Variations in precipitation can affect various aspects of people's lives, such as agriculture, industry, tourism, etc. Accurate rainfall predictions can assist in preparing for multiple activities and making the right decisions. Therefore, it is crucial to research predicting rainfall in Palembang. It is expected to simplify the prediction process and produce more accurate results. This research uses the Gated Recurrent Unit (GRU) and Long-Shorted Term Memory (LSTM) methods to make daily rainfall predictions for the next month using weather element data for ten (10) years in Palembang, utilizing the deep learning method. The hyperparameter model tuning experiment was conducted to obtain the best prediction results. From the research results, it can be concluded that the LSTM model is overall better than the GRU model in predicting daily rainfall in Palembang City. GRU has RMSE 9.33 and R2 0.54, while the LSTM Model has RMSE 7.45 and R2 0.70.

Item Type: Article
Uncontrolled Keywords: Rainfall, Prediction, Gated Recurrent Unit (GRU), Long-Shorted Term Memory (LSTM)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Depositing User: Unnamed user with email masilah.mansor@newinti.edu.my
Date Deposited: 23 Mar 2023 07:21
Last Modified: 13 Jul 2023 08:33
URI: http://eprints.intimal.edu.my/id/eprint/1730

Actions (login required)

View Item View Item