Forecasting Curah Hujan Di Bojonegoro Menggunakan Model CNN-CA-LSTM dan Metode Harmonic Dataset Distillation
DOI:
https://doi.org/10.32493/jiup.v11i2.60516Keywords:
harmonic dataset distillation, attention module, deep learning, forecastingAbstract
Rainfall forecasting in Bojonegoro region of Indonesia presents significant challenge due seasonal weather fluctuations and challenges of rainless days, which result in large number of zero data points or zero inflation. This study utilizes historical rainfall datasets in Bojonegoro since 1960, aggregated monthly with total 797 data, to explore deep learning architectures with Attention Module mechanisms and data optimization techniques to optimize model evaluation results. This study explores the CNN-LSTM model with modified Attention Module in the form of Coordinate Attention (CA) and evaluates it on baseline model. This study employs Harmonic Dataset Distillation (HDD) method, a novelty of this study, to improve computational efficiency through frequency domain data compression using the HDD method, and to maintain long-term seasonal patterns. The results of comparative analysis on CNN-LSTM with feature extraction model CNN-CA-LSTM Backbone model and the Basic Model can reduce training computation time by up to 73.66%. The Model CNN-CA-LSTM maintained good performance values in the Baseline Model, got an R2 of 0.78 with an RMSE result of 68.38, with the CNN-CA-LSTM Proposed Model with CNN-CA-LSTM Backbone got an R2 of 0.75 and an RMSE of 72.24.
References
H. Mulyanti, S. I. Purwaningrum, Y. L. A. D. Putra, A. A. Saputra, and B. Saputra, “Studi Adaptasi Perubahan Iklim pada Wilayah Pertanian Rawan Banjir di Kabupaten Bojonegoro,” Bojonegoro, Feb. 2026. Accessed: Jun. 29, 2026. [Online]. Available: https://repository.unigoro.ac.id/id/eprint/4966
C. Sika Azkia, Y. Ansori, F. Darnis, and A. Rahman, “Pengaruh Feature Engineering Time Series Berbasis Rolling Statistics untuk Prediksi Suhu Menggunakan Random Forest dan Gradient Boosting,” Jurnal Informatika Universitas Pamulang, vol. 11, no. 1, pp. 25–36, 2026, https://doi.org/10.32493/jiup.v11i1.58137.
A. Pico, M. A. Gonzalez-Sierra, and J. C. Martinez-Santos, “Machine Learning-Based Modeling of Reservoir Inflows from Precipitation Data,” in C3 2025 - IEEE Colombian Caribbean Conference, Institute of Electrical and Electronics Engineers Inc., 2025. https://doi.org/10.1109/C366505.2025.11339989
M. El Hafyani, K. El Himdi, and S. E. El Adlouni, “Improving monthly precipitation prediction accuracy using machine learning models: a multi-view stacking learning technique,” Frontiers in Water, vol. 6, 2024, https://doi.org/10.3389/frwa.2024.1378598
A. Y. Barrera-Animas, L. O. Oyedele, M. Bilal, T. D. Akinosho, J. M. D. Delgado, and L. A. Akanbi, “Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting,” Machine Learning with Applications, vol. 7, p. 100204, Mar. 2022, https://doi.org/10.1016/j.mlwa.2021.100204
E. G. A. Osman and F. A. Otaibi, “Integrating deep learning and econometrics for stock price prediction : A comprehensive comparison of LSTM , transformers , and traditional time series models,” Machine Learning with Applications, vol. 22, no. September, p. 100730, 2025, https://doi.org/10.1016/j.mlwa.2025.100730.
K. Indra Jaya, A. Mulyanti Suhartini, N. Jariyatin, and D. Septiani, “Prediksi Indeks Harga Saham Gabungan Indonesia Menggunakan Model CNN-CA-LSTM dan Aplikasi Website Streamlit,” Jurnal Mahasiswa Teknik Informatika, vol. 10, no. 1, Feb. 2026. https://doi.org/10.36040/jati.v10i1.16901
A. Wijayanto, A. Sugiharto, and R. Santoso, “Identifikasi Dini Curah Hujan Berpotensi Banjir Menggunakan Algoritma Long Short-Term Memory (LSTM) Dan Isolation Forest,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 3, pp. 637–646, Jul. 2024, https://doi.org/10.25126/jtiik.938718
M. Bilgili, E. Pinar, and T. Durhasan, “Global monthly sea surface temperature forecasting using the SARIMA, LSTM, and GRU models,” Earth Sci. Inform., vol. 18, no. 1, Jan. 2025, https://doi.org/10.1007/s12145-024-01585-z
S. Hong, S. Jang, W. Kweon, S. Kim, G. Lee, and H. Yu, “Harmonic Dataset Distillation for Time Series Forecasting,” AAAI Conference on Artificial Intelligence, 2026, doi: https://doi.org/10.1609/aaai.v40i26.39328.
W. Du et al., “An improved ResNet method for urban flooding water depth estimation from social media images,” Measurement (Lond)., vol. 242, Jan. 2025, https://doi.org/10.1016/j.measurement.2024.116114
Q. Hou, D. Zhou, and J. Feng, “Coordinate attention for efficient mobile network design,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 13708–13717, 2021, https://doi.org/10.1109/CVPR46437.2021.01350
M. Khalid, S. Deivasigamani, S. V, and S. Rajendran, “An efficient colorectal cancer detection network using atrous convolution with coordinate attention transformer and histopathological images,” Sci. Rep., vol. 14, no. 1, Dec. 2024, https://doi.org/10.1038/s41598-024-70117-y
Y. Cai, R. Zhao, H. Wang, L. Chen, Y. Lian, and Y. Zhong, “CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data,” IEEE Access, vol. 11, pp. 16203–16212, 2023, https://doi.org/10.1109/ACCESS.2023.3245146
S. Pan et al., “Oil well production prediction based on CNN-LSTM model with self-attention mechanism,” Energy, vol. 284, no. January, p. 128701, 2023, https://doi.org/10.1016/j.energy.2023.128701
B. Ladjal et al., “Hybrid deep learning CNN-LSTM model for forecasting direct normal irradiance: a study on solar potential in Ghardaia, Algeria,” Sci. Rep., vol. 15, no. 1, Dec. 2025, https://doi.org/10.1038/s41598-025-94239-z
K. Muchtar, S. Member, Y. Hafifah, and A. Febriana, “Edge AI-Based Detection for Defective Coffee Beans Using Deep Learning and Streamlit Framework,” IEEE Access, vol. 13, no. April, pp. 67977–67992, 2025, https://doi.org/10.1109/ACCESS.2025.3561189
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Kurniawan Indra Jaya; Andi Mulyanti Suhartini, Nurul Jariyatin, Devi Septiani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Jurnal Informatika Universitas Pamulang have CC-BY-NC or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Jurnal Informatika Universitas Pamulang recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY-NC or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
Jurnal Informatika Universitas Pamulang is licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
YOU ARE FREE TO:
- Share : copy and redistribute the material in any medium or format
- Adapt : remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms
This work is licensed under a 