Pemodelan Spasial-Temporal Kejadian Banjir Menggunakan Random Forest Regression dan Long Short-Term Memory untuk Mitigasi
-
Mochamad Amry Assiva
*
Institut Teknologi dan Bisnis Muhammadiyah Grobogan, Grobogan,
Indonesia
- Hadi Tanuji Institut Teknologi dan Bisnis Muhammadiyah Grobogan, Grobogan, Indonesia
- Eka Renny Noviati Wahyuni Institut Teknologi dan Bisnis Muhammadiyah Grobogan, Grobogan, Indonesia
- Muhammad Fa'iq Robbani Institut Teknologi dan Bisnis Muhammadiyah Grobogan, Grobogan, Indonesia (*) Corresponding Author
Abstract
This study evaluates a spatial-temporal flood-event modeling framework using Random Forest (RF) and Long Short-Term Memory (LSTM). RF estimates the number of flood events in 2025 across 19 districts using five disaster indicators from 2024 and mean elevation. Dry-season intake discharge was excluded because the available dam inventory does not provide a consistent series of observed discharge values. RF was evaluated using leave-one-out cross-validation (LOOCV). Reproduction of the BPBD + elevation model yielded MAE 2.122, RMSE 2.650, and R² -0.531. LSTM modeled monthly rainfall from two BMKG stations for August 2024–July 2026. The three-month look-back configuration achieved MAE 117.34 mm, RMSE 157.09 mm, and R² −0.313, compared with a persistence baseline MAE of 153.85 mm and RMSE of 216.14 mm. Given only 19 spatial units and 24 monthly rainfall observations, RF and LSTM are framed as a decision-support framework rather than a validated operational prediction system. The findings highlight the importance of out-of-sample evaluation, data-availability audits, and transparent reporting of limitations. The contribution of this study is to evaluate RF using LOOCV and topographic-feature comparisons, report prediction errors at the district level, compare LSTM with a persistence baseline, and audit hydrological data limitations.
Downloads
References
Q. B. Pham et al., “Evaluation of various boosting ensemble algorithms for predicting flood hazard susceptibility areas,” Geomatics, Nat. Hazards Risk, vol. 12, no. 1, pp. 2607–2628, Jan. 2021, doi: 10.1080/19475705.2021.1968510.
S. A. Abu El-Magd, “Random forest and naïve Bayes approaches as tools for flash flood hazard susceptibility prediction, South Ras El-Zait, Gulf of Suez Coast, Egypt,” Arab. J. Geosci., vol. 15, no. 3, p. 217, Feb. 2022, doi: 10.1007/s12517-022-09531-3.
C. Singha, V. K. Rana, Q. B. Pham, D. C. Nguyen, and E. Łupikasza, “Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment,” Environ. Sci. Pollut. Res., vol. 31, no. 35, pp. 48497–48522, Jul. 2024, doi: 10.1007/s11356-024-34286-7.
R. Abedi, R. Costache, H. Shafizadeh-Moghadam, and Q. B. Pham, “Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees,” Geocarto Int., vol. 37, no. 19, pp. 5479–5496, Oct. 2022, doi: 10.1080/10106049.2021.1920636.
S. E. Purwati and Y. Pristyanto, “Model Random Forest and Support Vector Machine for Flood Classification in Indonesia,” sinkron, vol. 8, no. 4, pp. 2261–2268, Oct. 2024, doi: 10.33395/sinkron.v8i4.13973.
M. R. Perdana Putra, Rama Ashari, Muhirin, Azib Widad Zuhaily Imam, and Kusrini, “Flood Prediction Using Machine Learning Model Integrated with Geographical Information System,” Khazanah Inform. J. Ilmu Komput. dan Inform., vol. 10, no. 2, pp. 121–126, Mar. 2025, doi: 10.23917/khif.v10i2.3723.
F. A. A. Hadi et al., “Machine learning techniques for flood forecasting,” J. Hydroinformatics, vol. 26, no. 4, pp. 779–799, Apr. 2024, doi: 10.2166/hydro.2024.208.
J. Zhou, L. Chen, T. Hu, H. Lu, Y. Shi, and L. Chen, “The comparative study of machine learning agent models in flood forecasting for tidal river reaches,” Sci. Rep., vol. 15, no. 1, p. 19130, May 2025, doi: 10.1038/s41598-025-04633-w.
V. Kumar, H. M. Azamathulla, K. V. Sharma, D. J. Mehta, and K. T. Maharaj, “The State of the Art in Deep Learning Applications, Challenges, and Future Prospects: A Comprehensive Review of Flood Forecasting and Management,” Sustainability, vol. 15, no. 13, p. 10543, Jul. 2023, doi: 10.3390/su151310543.
Y. Zhang, S. Ragettli, P. Molnar, O. Fink, and N. Peleg, “Generalization of an Encoder-Decoder LSTM model for flood prediction in ungauged catchments,” J. Hydrol., vol. 614, p. 128577, Nov. 2022, doi: 10.1016/j.jhydrol.2022.128577.
Z. Cui, S. Guo, Y. Zhou, and J. Wang, “Exploration of dual-attention mechanism-based deep learning for multi-step-ahead flood probabilistic forecasting,” J. Hydrol., vol. 622, p. 129688, Jul. 2023, doi: 10.1016/j.jhydrol.2023.129688.
Balai Besar Wilayah Sungai Pemali Juana, “Data Sumber Daya Air,” Kementerian Pekerjaan Umum. Accessed: Aug. 04, 2026. [Online]. Available: https://sda.pu.go.id/balai/bbwspemalijuana/pages/informasisetiapsaat
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed. Sebastopol, CA, USA: O’Reilly Media, 2022.
F. Chollet, Deep Learning with Python, 2nd ed. Shelter Island, NY, USA: Manning Publications, 2021.
M. A. Assiva, “Analisis sentimen terhadap pariwisata di Kabupaten Grobogan berbasis Orange menggunakan Naive Bayes,” Innov. J. Soc. Sci. Res., vol. 4, no. 6, pp. 2351–2359, 2024, doi: 10.31004/innovative.v4i6.16469.
A. Saleh, A. Yuzir, N. Sabtu, S. K. M. Abujayyab, M. R. Bunmi, and Q. B. Pham, “Flash flood susceptibility mapping in urban area using genetic algorithm and ensemble method,” Geocarto Int., vol. 37, no. 25, pp. 10199–10228, Dec. 2022, doi: 10.1080/10106049.2022.2032394.
M. Wahba, R. Essam, M. El-Rawy, N. Al-Arifi, F. Abdalla, and W. M. Elsadek, “Forecasting of flash flood susceptibility mapping using random forest regression model and geographic information systems,” Heliyon, vol. 10, no. 13, p. e33982, Jul. 2024, doi: 10.1016/j.heliyon.2024.e33982.
L. Zhang, H. Qin, J. Mao, X. Cao, and G. Fu, “High temporal resolution urban flood prediction using attention-based LSTM models,” J. Hydrol., vol. 620, p. 129499, May 2023, doi: 10.1016/j.jhydrol.2023.129499.
B. Sabzipour et al., “Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment,” J. Hydrol., vol. 627, p. 130380, Dec. 2023, doi: 10.1016/j.jhydrol.2023.130380.
J. S. Navarro, R. Zhuang, C. Albertini, and S. Manfreda, “Mapping flood susceptibility using Random Forest exploiting satellite observations and geomorphic features,” Sci. Total Environ., vol. 1002, p. 180592, Nov. 2025, doi: 10.1016/j.scitotenv.2025.180592.
B. L. Al Zakina, Z. Zainuddin, T. B. Santoso, and L. Safitri, “Penyuluhan Mitigasi Bencana Banjir Sebagai Upaya Kesiapsiagaan Bencana Di Kota Purwodadi,” J. Hum. Educ., vol. 4, no. 4, pp. 80–84, Jul. 2024, doi: 10.31004/jh.v4i4.1147.
Badan Meteorologi Klimatologi dan Geofisika, “Data Online Meteorologi, Klimatologi, dan Geofisika,” Badan Meteorologi, Klimatologi, dan Geofisika. Accessed: Aug. 04, 2026. [Online]. Available: https://dataonline.bmkg.go.id/dataonline-home
M. Waqas and U. W. Humphries, “A critical review of RNN and LSTM variants in hydrological time series predictions,” MethodsX, vol. 13, p. 102946, 2024, doi: 10.1016/j.mex.2024.102946.
N. Byaruhanga, D. Kibirige, S. Gokool, and G. Mkhonta, “Evolution of flood prediction and forecasting models for flood early warning systems: A scoping review,” Water, vol. 16, no. 13, p. 1763, 2024, doi: 10.3390/w16131763.
M. Asif, M. M. Kuglitsch, I. Pelivan, and R. Albano, “Review and Intercomparison of Machine Learning Applications for Short-term Flood Forecasting,” Water Resour. Manag., vol. 39, no. 5, pp. 1971–1991, Mar. 2025, doi: 10.1007/s11269-025-04093-x.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Pemodelan Spasial-Temporal Kejadian Banjir Menggunakan Random Forest Regression dan Long Short-Term Memory untuk Mitigasi
Pages: 113-123
Copyright (c) 2026 Mochamad Amry Assiva, Hadi Tanuji, Eka Renny Noviati Wahyuni, Muhammad Fa'iq Robbani
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).
