Paper · 2026 · Open access
Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models
Lecture notes in electrical engineering, 380–396 · Published 2 July 2026 · DOI 10.1007/978-3-032-25259-3_30
In brief
“Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models” is a 2026 paper by Dodi Sudiana and Abyaz Attaqee Shah Oktora, published in Lecture notes in electrical engineering. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at Lecture notes in electrical engineering.
- Citations
- 0
- References
- 18
- Authors
- 2
Abstract
Rainfall forecasting plays a crucial role in mitigating the impacts of extreme weather events, particularly in regions such as Jakarta, where accurate predictions are essential for urban planning and flood prevention. This study investigates the performance of tree-based machine learning models—Random Forest (RF) and XGBoost—as well as deep learning models, including Long Short-Term Memory (LSTM) and a hybrid LSTM–Transformer architecture, for daily rainfall forecasting using time-series data. The dataset consists of daily meteorological observations collected in Jakarta between 2010 and 2020. All models are formulated under a one-step-ahead forecasting framework and trained using a chronological data-splitting strategy to reflect realistic operational conditions. Model configurations are obtained through systematic hyperparameter optimization, with tree-based models emphasizing ensemble robustness and controlled complexity, while deep learning architectures are designed to capture both local and global temporal dependencies in rainfall patterns. Model performance is evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The results indicate that RF outperforms XGBoost on larger datasets, achieving an error improvement of 84.22%, whereas XGBoost performs better on smaller datasets with an improvement of 27.86% but shows declining performance as data complexity increases. LSTM and LSTM–Transformer models exhibit comparable performance, with only a 0.73% difference in error, suggesting limited additional benefit from attention mechanisms under the studied data conditions. Overall, the findings highlight the importance of aligning model complexity with dataset characteristics to achieve robust and reliable rainfall forecasting in urban environments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Sudiana, D., & Oktora, A. A. S. (2026). Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models. Lecture notes in electrical engineering, 380–396. https://doi.org/10.1007/978-3-032-25259-3_30
MLA 9
Sudiana, Dodi, and Abyaz Attaqee Shah Oktora. “Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models.” Lecture notes in electrical engineering, 2026, pp. 380–396. https://doi.org/10.1007/978-3-032-25259-3_30.
Chicago
Sudiana, Dodi and Abyaz Attaqee Shah Oktora. 2026. “Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models.” Lecture notes in electrical engineering: 380–396. https://doi.org/10.1007/978-3-032-25259-3_30.
Harvard
Sudiana, D. and Oktora, A. A. S. (2026) ‘Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models’, Lecture notes in electrical engineering, pp. 380–396. doi:10.1007/978-3-032-25259-3_30.
IEEE
D. Sudiana and A. A. S. Oktora, “Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models,” Lecture notes in electrical engineering, pp. 380–396, 2026, doi: 10.1007/978-3-032-25259-3_30.
BibTeX
@article{sudiana2026rainfall,
title = {{Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models}},
author = {Sudiana, Dodi and Oktora, Abyaz Attaqee Shah},
journal = {Lecture notes in electrical engineering},
year = {2026},
pages = {380--396},
doi = {10.1007/978-3-032-25259-3_30},
url = {https://doi.org/10.1007/978-3-032-25259-3_30}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- precipitation forecasting
- daily precipitation
- Jakarta
- random forest
- XGBoost
- LSTM
- Transformer attention mechanism
- tree-based ensemble models
Work with this paper
Most-cited papers in Environmental Science
- Biodiversity hotspots for conservation prioritiesNorman Myers, Russell A. Mittermeier, Cristina Goettsch Mittermeier and 2 more · Nature · 2000 · 32,720 citations
- The Tragedy of the CommonsGarrett Hardin · Science · 1968 · 26,194 citations
- River flow forecasting through conceptual models part I — A discussion of principlesJ.E. Nash, John V. Sutcliffe · Journal of Hydrology · 1970 · 24,625 citations
- The value of the world's ecosystem services and natural capitalRobert Costanza, Ralph C. d’Arge, R.S. de Groot and 10 more · Nature · 1997 · 23,508 citations
- Climate change 2007: the physical science basisSusan Solomon, Dahe Qin, Martin Manning and 5 more · 2007 · 23,383 citations
Questions about this paper
How do I cite this paper in APA style?
Sudiana, D., & Oktora, A. A. S. (2026). Rainfall Forecasting in Jakarta Using Machine Learning and Transformer-Based Time Series Models. Lecture notes in electrical engineering, 380–396. https://doi.org/10.1007/978-3-032-25259-3_30
How many times has this paper been cited?
0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Lecture notes in electrical engineering: sign in and open the full text from this page.
Who wrote this paper?
Dodi Sudiana, Abyaz Attaqee Shah Oktora.
What is the DOI of this paper?
10.1007/978-3-032-25259-3_30, permanently at https://doi.org/10.1007/978-3-032-25259-3_30. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.