Komparasi Model LSTM dan CNN-LSTM untuk Peramalan Curah Hujan di Kota Tangerang Selatan
-
Uliyatunisa
*
Universitas Pamulang,
Indonesia
- Dahlan Supriatna Universitas Pamulang, Indonesia
Abstract
This study compares the performance of Long Short-Term Memory (LSTM) and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) models for daily rainfall forecasting in South Tangerang City using meteorological data from January 2005 to July 2025. Data from official meteorological stations was processed with mean imputation for missing values and MinMaxScaler normalization. Models were evaluated based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and coefficient of determination R². Results show CNN-LSTM outperforms with RMSE 0.79, MAE 0.63, MSE 0.62, and R² 0.61, compared to LSTM (RMSE 0.83, MAE 0.60, MSE 0.68, R² 0.58). Prediction visualizations confirm CNN-LSTM's accuracy in capturing extreme patterns, with statistically significant differences via t-test. The novelty lies in using a long-term (20-year) dataset for tropical Indonesia, demonstrating the hybrid model's efficacy for complex spatio-temporal predictions. Findings support flood early warning systems and water resource management, recommending additional climate variable integration for further development.
References
D. A. Setiyowati and M. Ariska, “Analisis Pola Curah Hujan Di Pulau Jawa Dengan Menggunakan Empirical Orthogonal Function (EOF),” J. Pendidik. Fis. dan Sains, vol. 7, no. 2, pp. 120–128, Sep. 2024, doi: 10.52188/jpfs.v7i2.788.
L. A. Al-Samrraie et al., “Deep Learning Models Based on CNN, RNN, and LSTM for Rainfall Forecasting: Jordan as a Case Study,” Math. Model. Eng. Probl., vol. 12, no. 7, pp. 2456–2466, Jul. 2025, doi: 10.18280/mmep.120724.
A. Azi and K. Kusrini, “Rainfall Prediction in Jayapura City Area Using Long Short-Term Memory,” J. Comput. Networks, Archit. High Perform. Comput., vol. 7, no. 2, pp. 433–439, Apr. 2025, doi: 10.47709/cnahpc.v7i2.5506.
A. M. L. Harefa, R. Antoni, A. I. Sitepu, Y. F. Limbong, and M. S. Novelan, “Enhanced Rainfall Forecasting Through Deep Learning Optimization Using Long Short-Term Memory Networks,” RIGGS J. Artif. Intell. Digit. Bus., vol. 4, no. 2, pp. 274–284, May 2025, doi: 10.31004/riggs.v4i2.487.
F. I. Arassah, K. Sadik, B. Sartono, and P. Sofan, “Optimizing Machine Learning for Daily Rainfall Prediction in Bogor: A Statistical Downscaling Approach,” Eduvest - J. Univers. Stud., vol. 5, no. 6, pp. 7006–7018, Jun. 2025, doi: 10.59188/eduvest.v5i6.51307.
Z. N. Ruslana and E. Zuliarso, “Rainfall Forecasting Using SSA-Based Hybrid Models with LSSVR and LSTM for Disaster Mitigation,” vol. 6, no. 4, pp. 2079–2106, 2025.
N. A. Fadhilah et al., “Long Short-Term Memory as a Rainfall Forecasting Model for Bogor City in 2025-2026,” J. Appl. Informatics Comput., vol. 9, no. 2, pp. 333–340, Mar. 2025, doi: 10.30871/jaic.v9i2.9068.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, doi: 10.1109/5.726791.
S. Samantaray, A. Sahoo, and D. P. Satapathy, “Rainfall Prediction using Hybrid CNN-LSTM approach: A case study in the Boudh district, Odisha, India,” Mar. 18, 2025. doi: 10.5194/egusphere-egu25-1542.
M. F. Putranto and R. Munir, “Deep Learning Approach for Heavy Rainfall Prediction Using Himawari-8 and RDCA Data,” Proc. - 2023 10th Int. Conf. Comput. Control. Informatics its Appl. Explor. Power Data Leveraging Inf. to Drive Digit. Innov. IC3INA 2023, pp. 424–429, 2023, doi: 10.1109/IC3INA60834.2023.10285744.
B. K. Cahyono et al., “Leveraging machine learning and open accessed remote sensing data for precise rainfall forecasting,” Commun. Sci. Technol., vol. 10, no. 1, pp. 135–147, Jul. 2025, doi: 10.21924/cst.10.1.2025.1638.
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, p. 15404, May 2025, doi: 10.1038/s41598-025-94239-z.
E. Pitaloka and S. S. Tegar Bagus Agung Hartanto, “Penerapan Machine Learning Untuk Prediksi Bencana Banjir,” J. Sist. Inf. Bisnis, vol. 14, no. 1, pp. 62–76, 2024, doi: 10.21456/vol14iss1pp62-76.
E. Lee et al., “Characterization of naturally occurring radioactive material dynamics in community water systems using groundwater from Ganghwa Island, Republic of Korea,” J. Hydrol., vol. 628, p. 130512, Jan. 2024, doi: 10.1016/j.jhydrol.2023.130512.
Nurfalinda, M. Al Fiani, and M. R. Rathomi, “Prediksi Temperatur Maksimum di Kota Tanjungpinang Menggunakan Model CNN-LSTM,” Komputa J. Ilm. Komput. dan Inform., vol. 14, no. 1, pp. 129–138, May 2025, doi: 10.34010/komputa.v14i1.15377.
R. Yuan, “Rainfall prediction based on CNN-LSTM model under sliding window,” Eur. J. Remote Sens., vol. 58, no. 1, Dec. 2025, doi: 10.1080/22797254.2025.2540106.
A. Saleh, M. L. Tan, Z. M. Yaseen, and F. Zhang, “Integrated machine learning models for enhancing tropical rainfall prediction using NASA POWER meteorological data,” J. Water Clim. Chang., vol. 15, no. 12, pp. 6022–6042, Dec. 2024, doi: 10.2166/wcc.2024.719.
V. Monita, Sevirda Raniprima, and Nanang Cahyadi, “Comparative Analysis of Daily and Weekly Heavy Rain Prediction Using LSTM and Cloud Data,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 10, no. 4, pp. 833–842, 2024, doi: 10.26555/jiteki.v10i4.30374.
A. Rasheeda Satheesh, P. Knippertz, and A. H. Fink, “Machine Learning Models for Daily Rainfall Forecasting in Northern Tropical Africa Using Tropical Wave Predictors,” Weather Forecast., vol. 40, no. 10, pp. 1895–1916, Oct. 2025, doi: 10.1175/WAF-D-24-0192.1.
M. Sinambela, S. Humaidi, and M. Situmorang, “Application of Convolutional Neural Networks ( CNN ) for Optimizing Route Changes Based on Dynamic Weather Conditions and Travel Time,” pp. 183–197.
S. Salma and A. Ashwitha, “Hybrid Cnn-Lstm Model: Rainfall Analysis and Prediction for Karnataka Region,” J. Theor. Appl. Inf. Technol., vol. 100, no. 22, pp. 6715–6716, 2022.
Copyright (c) 2025 Uliyatunisa, Dahlan Supriatna
This work is licensed under a Creative Commons Attribution 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 Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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 (Refer to The Effect of Open Access).
.png)
.png)
