Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 2

Rainfall Intensity Prediction Using LSTM and Random Forest Hybrid Model

IJCCS (Indonesian Journal of Computing and Cybernetics Systems) · Vol. 20 No. 1 (2026) · pp. 107–118

DOI
10.22146/ijccs.109189
ISSN
2460-7258, 1978-1520
Published
2026-01-31
Publisher
IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Predicting rainfall accurately is essential for managing water resources and preventing hydrometeorological disasters. The unpredictability of daily rainfall patterns necessitates accurate and effective prediction methods. This study proposes a residual hybrid approach to forecast rainfall using historical rainfall data alone. To record temporal information, a Long Short-Term Memory (LSTM) model is used. patterns in the time series data and generate initial predictions. The residual, defined as the difference between actual values and LSTM predictions, is then used as the intend to use a Random Forest (RF) model for training, which learns the non-linear patterns not effectively captured by the LSTM. Although the dataset includes various meteorological variables such as temperature and humidity, this study uses only rainfall as the main input. The data is split into training and testing sets with an 80:20 ratio. Model performance is evaluated using MAE, MSE, and RMSE, with RMSE as the primary evaluation metric. Experimental results show that the LSTM-RF hybrid model consistently delivers greater accuracy of predictions in comparison to single-model approaches, demonstrating strong potential in improving the reliability of rainfall forecasting based solely on historical data.

Keywords

Collaboration network of the authors

5 authors · 6 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Esa Unggul
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Habibullah AkbarUniversitas Esa Unggul1
Ferdinand Defin DelioUniversitas Esa Unggul1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.ugm.ac.id/ijccs/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Rainfall Intensity Prediction Using LSTM and Random Forest Hybrid Model</dc:title>
	<dc:creator>Pambudi, Ari</dc:creator>
	<dc:creator>Aryani, Diah</dc:creator>
	<dc:creator>Sunarto, Ronald Nur</dc:creator>
	<dc:subject xml:lang="en-US">Computer Science</dc:subject>
	<dc:subject xml:lang="en-US">Machine Learning; Rainfall prediction; Long Short-Term Memory; Random Forest; Hybrid Model; Weather Forecasting; Time Series</dc:subject>
	<dc:description xml:lang="en-US">Predicting rainfall accurately is essential for managing water resources and preventing hydrometeorological disasters. The unpredictability of daily rainfall patterns necessitates accurate and effective prediction methods. This study proposes a residual hybrid approach to forecast rainfall using historical rainfall data alone. To record temporal information, a Long Short-Term Memory (LSTM) model is used. patterns in the time series data and generate initial predictions. The residual, defined as the difference between actual values and LSTM predictions, is then used as the intend to use a Random Forest (RF) model for training, which learns the non-linear patterns not effectively captured by the LSTM. Although the dataset includes various meteorological variables such as temperature and humidity, this study uses only rainfall as the main input. The data is split into training and testing sets with an 80:20 ratio. Model performance is evaluated using MAE, MSE, and RMSE, with RMSE as the primary evaluation metric. Experimental results show that the LSTM-RF hybrid model consistently delivers greater accuracy of predictions in comparison to single-model approaches, demonstrating strong potential in improving the reliability of rainfall forecasting based solely on historical data.</dc:description>
	<dc:publisher xml:lang="en-US">IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2026-01-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.ugm.ac.id/ijccs/article/view/109189</dc:identifier>
	<dc:identifier>10.22146/ijccs.109189</dc:identifier>
	<dc:source xml:lang="en-US">IJCCS (Indonesian Journal of Computing and Cybernetics Systems); Vol 20, No 1 (2026): January; 107-118</dc:source>
	<dc:source>2460-7258</dc:source>
	<dc:source>1978-1520</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.ugm.ac.id/ijccs/article/view/109189/43434</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>