Comparative Analysis of Machine Learning Models for Water Level Forecasting towards Flood Early Warning in the Mekong River
DOI:
https://doi.org/10.37936/ecti-eec.2027251.262931Keywords:
Flood prediction, Water level forecasting, Mekong River, Long Short-Term MemoryAbstract
Flooding is a recurring hazard in Thailand, particularly in Nong Khai, causing significant socioeconomic impacts. Traditional hydrological models struggle to capture the complex nonlinear behavior of multi-station water-level systems. This study compares deep learning architectures with classical machine learning models for water-level forecasting. The research evaluates four distinct models:two recurrent neural network (RNN) architectures—Long Short-Term Memory (LSTM) and Gated Recurrent Units
(GRU)—and two non-RNN baselines—Random Forest (RF) and Support Vector Machine (SVM). All models are trained and validated on a 19-year hydrological time-series dataset (2006–2025) comprising daily water level measurements from five key monitoring stations along the Mekong River. Performance was assessed using Root Mean Square Error (RMSE) and Mean Absolute Error
(MAE) metrics. Results indicate that while all four models successfully capture primary seasonal trends, the RNN based models (LSTM and GRU) outperform the classical ensemble (RF) and kernel-based regression (SVM) methods. The LSTM model demonstrated the highest predictive accuracy, achieving the lowest error rates with an RMSE of 0.3459 and an MAE of 0.1196. These results suggest that LSTM’s sequence-based memory gates provide superior capability in modeling complex hydrological fluctuations. Consequently, the LSTM is the foundational architecture for a future hydrological Digital Twin of the Mekong River Basin, designed to integrate tributary data for holistic flood simulation and operational decision support.
Downloads
References
T. Boonnuk, K. Poomphakwaen, and N. Kumyoung, “Application for simulating public health problems during floods around the Loei River in Thailand: the implementation of a geographic information system and structural equation model,” BMC Public Health, vol. 22, no. 1, Dec. 2022, doi: 10.1186/s12889-022-14018-7.
S. Chantee and T. Mayakul, “Modeling Flood Susceptible Areas Using Deep Learning Techniques with Random Subspace: A Case Study of the Mae Chan Basin in Thailand,” vol. 14, no. 1, 2024.
H. H. Loc, A. Emadzadeh, E. Park, P. Nontikansak, and R. C. Deo, “The Great 2011 Thailand flood disaster revisited: Could it have been mitigated by different dam operations based on better weather forecasts?,” Environ Res, vol. 216, p. 114493, Jan. 2023, doi: 10.1016/J.ENVRES.2022.114493.
W. Ariyasirichot, “The Policy Design on Preparation and Coping with Flash Flood Mekong River Basin Entrance Inequality Deduction Form Disaster: A Case Study of Mueang Nong Khai District Nong Khai Province, Thailand,” Turkish Journal of Computer and Mathematics Education, vol. 12, pp. 4106–4112, 2021.
N. Tsumita, S. Piyapong, R. Kaewkluengklom, S. Jaensirisak, and A. Fukuda, “Flood susceptibility mapping of urban flood risk: comparing autoencoder multilayer perceptron and logistic regression models in Ubon Ratchathani, Thailand,” Natural Hazards, vol. 121, no. 15, pp. 17833–17867, Aug. 2025, doi: 10.1007/s11069-025-07494-8.
W. Pratoomchai, C. Ekkawatpanit, N. Yoobanpot, and K. T. Lee, “A Dilemma between Flood and Drought Management: Case Study of the Upper Chao Phraya Flood-Prone Area in Thailand,” Water (Switzerland), vol. 14, no. 24, Dec. 2022, doi: 10.3390/w14244056.
T. Wiangwiset et al., “Design and Implementation of a Real-Time Crowd Monitoring System Based on Public Wi-Fi Infrastructure: A Case Study on the Sri Chiang Mai Smart City,” Smart Cities 2023, Vol. 6, Pages 987-1008, vol. 6, no. 2, pp. 987–1008, Mar. 2023, doi: 10.3390/SMARTCITIES6020048.
I. M. Chathuranika et al., “Comparison of Two Hydrological Models, HEC-HMS and SWAT in Runoff Estimation: Application to Huai Bang Sai Tropical Watershed, Thailand,” Fluids, vol. 7, no. 8, Aug. 2022, doi: 10.3390/fluids7080267.
M. N. Adli Zakaria et al., “Exploring machine learning algorithms for accurate water level forecasting in Muda river, Malaysia,” Heliyon, vol. 9, no. 7, Jul. 2023, doi: 10.1016/j.heliyon.2023.e17689.
V. K. Sharma, A. K. Shukla, V. M. Chowdary, S. Saran, and S. K. Srivastav, “Integration of recurrent neural network models and flood inundation extent libraries for flood forecasting,” Remote Sens Appl, vol. 39, p. 101649, Aug. 2025, doi: 10.1016/J.RSASE.2025.101649.
T. T. Hieu, T. Q. Chieu, D. N. Quang, and N. D. Hieu, “Water level prediction using deep learning models: A case study of the Kien Giang River, Quang Binh Province,” River, vol. 2, no. 4, pp. 468–479, Oct. 2023, doi: 10.1002/RVR2.63.
M. Cho, C. Kim, K. Jung, and H. Jung, “Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction,” Water (Switzerland), vol. 14, no. 14, Jul. 2022, doi: 10.3390/w14142221.
V. Atashi, H. T. Gorji, S. M. Shahabi, R. Kardan, and Y. H. Lim, “Water Level Forecasting Using Deep Learning Time‐Series Analysis: A Case Study of Red River of the North,” Water (Switzerland), vol. 14, no. 12, Jun. 2022, doi: 10.3390/w14121971.
M. Zhang et al., “Assessing Hydropower Impacts on Flood and Drought Hazards in the Lancang–Mekong River Using CNN-LSTM Machine Learning,” Water (Switzerland), vol. 17, no. 15, Aug. 2025, doi: 10.3390/w17152352.
Q. Chai, S. Zhang, Q. Tian, C. Yang, and L. Guo, “Daily Runoff Prediction Based on FA-LSTM Model,” Water (Switzerland), vol. 16, no. 16, Aug. 2024, doi: 10.3390/w16162216.
F. J. Hop, R. Linneman, B. Schnitzler, A. Bomers, and M. J. Booij, “Real time probabilistic inundation forecasts using a LSTM neural network,” J Hydrol (Amst), vol. 635, May 2024, doi: 10.1016/j.jhydrol.2024.131082.
M. Hasyimi, L. Nada, and F. Zain, “Journal of Innovative and Creativity Model Prediksi Ketinggian Air Disemua Pintu Muka Air Sungai Ciliwung Dengan Menggunakan Metode Long Short-Term Memory,” 2025.
G. K. Fordjour and A. Kalyanapu, “Implementing a GRU Neural Network for Flood Prediction in Ashland City, Tennessee,” May 2024, doi: 10.48550/ARXIV.2405.10375.
A. Gharehbaghi, R. Ghasemlounia, F. Ahmadi, and M. Albaji, “Groundwater level prediction with meteorologically sensitive Gated Recurrent Unit (GRU) neural networks,” J Hydrol (Amst), vol. 612, p. 128262, Sep. 2022, doi: 10.1016/J.JHYDROL.2022.128262.
Y. Zhang, Z. Zhou, J. Van Griensven Thé, S. X. Yang, and B. Gharabaghi, “Flood Forecasting Using Hybrid LSTM and GRU Models with Lag Time Preprocessing,” Water 2023, Vol. 15, Page 3982, vol. 15, no. 22, p. 3982, Nov. 2023, doi: 10.3390/W15223982.
F. Manokij, K. Sarinnapakorn, and P. Vateekul, “Cascading models of cnn and gru with autoencoder loss for precipitation forecast in Thailand,” ECTI Transactions on Computer and Information Technology, vol. 15, no. 3, pp. 333–346, 2021, doi: 10.37936/ecti-cit.2021153.240957.
K. Park, Y. Seong, Y. Jung, I. Youn, and C. K. Choi, “Development of Water Level Prediction Improvement Method Using Multivariate Time Series Data by GRU Model,” Water 2023, Vol. 15, Page 587, vol. 15, no. 3, p. 587, Feb. 2023, doi: 10.3390/W15030587.
M. Pan et al., “Water Level Prediction Model Based on GRU and CNN,” IEEE Access, vol. 8, pp. 60090–60100, 2020, doi: 10.1109/ACCESS.2020.2982433.
I. R. Widiasari and R. Efendi, “Utilizing LSTM-GRU for IOT-Based Water Level Prediction Using Multi-Variable Rainfall Time Series Data,” Informatics (Basel), vol. 11, no. 4, pp. 73–73, Oct. 2024, doi: 10.3390/INFORMATICS11040073.
M. Soliman, M. M. Morsy, and H. G. Radwan, “Generalized Methodology for Two-Dimensional Flood Depth Prediction Using ML-Based Models,” Hydrology, vol. 12, no. 9, Sep. 2025, doi: 10.3390/hydrology12090223.
Y. Liao, Z. Wang, C. Lai, and C. Y. Xu, “A Framework on Fast Mapping of Urban Flood Based on a Multi-Objective Random Forest Model,” International Journal of Disaster Risk Science, vol. 14, no. 2, pp. 253–268, Apr. 2023, doi: 10.1007/s13753-023-00481-2.
A. P. K. Anggraini, T. Trismadi, and A. A. Supriyadi, “Predicting Water Levels from Environmental Parameters Using Random Forest Models,” International Journal of Engineering Continuity, vol. 4, no. 1, pp. 39–53, Dec. 2025, doi: 10.58291/IJEC.V4I1.314.
W. Mobley, A. Sebastian, R. Blessing, W. E. Highfield, L. Stearns, and S. D. Brody, “Quantification of continuous flood hazard using random forest classification and flood insurance claims at large spatial scales: A pilot study in southeast Texas,” Natural Hazards and Earth System Sciences, vol. 21, no. 2, pp. 807–822, Mar. 2021, doi: 10.5194/nhess-21-807-2021.
L. Schoppa, M. Disse, and S. Bachmair, “Evaluating the performance of random forest for large-scale flood discharge simulation,” J Hydrol (Amst), vol. 590, p. 125531, Nov. 2020, doi: 10.1016/J.JHYDROL.2020.125531.
S. Asaly et al., “Predicting Eastern Mediterranean Flash Floods Using Support Vector Machines with Precipitable Water Vapor, Pressure, and Lightning Data,” Remote Sensing 2023, Vol. 15, vol. 15, no. 11, Jun. 2023, doi: 10.3390/RS15112916.
M.-J. Chang et al., “Long-Term Flooding Maps Forecasting System Using Series Machine Learning and Numerical Weather Prediction System,” Water 2022, Vol. 14, vol. 14, no. 20, Oct. 2022, doi: 10.3390/W14203346.
V. H. Nhu et al., “Daily water level prediction of zrebar lake (Iran): A comparison between m5p, random forest, random tree and reduced error pruning trees algorithms,” ISPRS Int J Geoinf, vol. 9, no. 8, Aug. 2020, doi: 10.3390/ijgi9080479.
Q. Wang and S. Wang, “Machine Learning-Based Water Level Prediction in Lake Erie,” Water 2020, Vol. 12, Page 2654, vol. 12, no. 10, p. 2654, Sep. 2020, doi: 10.3390/W12102654.
D. H. Hossoda, R. F. Perez, J. R. B. Tercini, and J. I. G. Bonnecarrère, “Data-Driven Modeling for Urban Flood Warning Systems: A Case Study in the Guarará Basin, Brazil,” J Flood Risk Manag, vol. 18, no. 3, Sep. 2025, doi: 10.1111/JFR3.70110.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Tanapattara Wongkhamchan, Ariya Namvong, Jakub Michel, Chayada Surawanitkun, Wullapa Wongsinlatam, Tawun Remsungnen, Thalerngsak Wiangwiset, Wichian Tong-Gate, Apirat Siritaratiwat
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
- Creative Commons Copyright License
The journal allows readers to download and share all published articles as long as they properly cite such articles; however, they cannot change them or use them commercially. This is classified as CC BY-NC-ND for the creative commons license.
- Retention of Copyright and Publishing Rights
The journal allows the authors of the published articles to hold copyrights and publishing rights without restrictions.
