Journal article · 2026 · Open access

Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors

Akhdan Fadhilah Yaskur Hardiano, Sonni Setiawan

Jurnal Meteorologi dan Geofisika, 26(2), 123–132 · Published 5 January 2026 · DOI 10.31172/jmg.v26i2.1194

Open PDFView at the publisherCite this paper

In brief

“Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors” is a 2026 journal article by Akhdan Fadhilah Yaskur Hardiano and Sonni Setiawan, published in Jurnal Meteorologi dan Geofisika. OpenAlex counts 1 citations as of 20 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at Jurnal Meteorologi dan Geofisika.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.33
References
27
Authors
2

Abstract

In this study, we developed and evaluated daily rainfall prediction models utilizing deep learning architectures, specifically comparing Long Short-Term Memory (LSTM) and Transformer models integrated with various atmospheric predictors. Our results indicate that the LSTM achieved superior accuracy at short-term lags—reaching an R² of 0.94 and an RMSE as low as 4.81 at lag-3—whereas the Transformer demonstrated higher consistency across all lags, maintaining stable R² values between 0.87 and 0.88. The application of a 5-day smoothing pre-processing step significantly enhanced prediction quality for both architectures by mitigating high-frequency noise, a benefit particularly pronounced in the LSTM due to its sensitivity to data fluctuations. Notably, the inclusion of tropical wave variables did not substantially improve model performance and, in some instances, reduced LSTM accuracy at longer lags by increasing input complexity; conversely, the Transformer remained robust to these additional variables. Among the predictors evaluated, Vertically Integrated Moisture Flux Divergence (VIMD) emerged as the most critical feature, underscoring its physical relevance to precipitation processes in convective and monsoonal regions. These findings suggest that while LSTMs excel at capturing immediate temporal dynamics, Transformers provide a more stable framework for longer-range rainfall forecasting in Jakarta.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Hardiano, A. F. Y., & Setiawan, S. (2026). Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors. Jurnal Meteorologi dan Geofisika, 26(2), 123–132. https://doi.org/10.31172/jmg.v26i2.1194

MLA 9

Hardiano, Akhdan Fadhilah Yaskur, and Sonni Setiawan. “Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors.” Jurnal Meteorologi dan Geofisika, vol. 26, no. 2, 2026, pp. 123–132. https://doi.org/10.31172/jmg.v26i2.1194.

Chicago

Hardiano, Akhdan Fadhilah Yaskur and Sonni Setiawan. 2026. “Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors.” Jurnal Meteorologi dan Geofisika 26 (2): 123–132. https://doi.org/10.31172/jmg.v26i2.1194.

Harvard

Hardiano, A. F. Y. and Setiawan, S. (2026) ‘Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors’, Jurnal Meteorologi dan Geofisika, 26(2), pp. 123–132. doi:10.31172/jmg.v26i2.1194.

IEEE

A. F. Y. Hardiano and S. Setiawan, “Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors,” Jurnal Meteorologi dan Geofisika, vol. 26, no. 2, pp. 123–132, 2026, doi: 10.31172/jmg.v26i2.1194.

BibTeX

@article{hardiano2026leveraging,
  title     = {{Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors}},
  author    = {Hardiano, Akhdan Fadhilah Yaskur and Setiawan, Sonni},
  journal   = {Jurnal Meteorologi dan Geofisika},
  year      = {2026},
  volume    = {26},
  number    = {2},
  pages     = {123--132},
  doi       = {10.31172/jmg.v26i2.1194},
  url       = {https://doi.org/10.31172/jmg.v26i2.1194}
}

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

  • daily rainfall prediction
  • LSTM
  • transformer models
  • climate predictors
  • tropical waves
  • data smoothing
  • short-term precipitation forecasting
  • monsoon rainfall

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Hardiano, A. F. Y., & Setiawan, S. (2026). Leveraging Sequential and Attention-Based Deep Learning Architectures for Accurate Daily Rainfall Prediction in Jakarta, Indonesia, Using Atmospheric Predictors. Jurnal Meteorologi dan Geofisika, 26(2), 123–132. https://doi.org/10.31172/jmg.v26i2.1194

How many times has this paper been cited?

1 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 Jurnal Meteorologi dan Geofisika: sign in and open the PDF from this page.

Who wrote this paper?

Akhdan Fadhilah Yaskur Hardiano, Sonni Setiawan.

What is the DOI of this paper?

10.31172/jmg.v26i2.1194, permanently at https://doi.org/10.31172/jmg.v26i2.1194. 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.