Hybrid deep learning models for daily river discharge prediction: lead-time performance analysis in Mymensingh, Bangladesh
Open Access
- 26 December 2025
- journal article
- Published by IWA Publishing in Water Practice & Technology
- Vol. 21 (1) , 240-265
Abstract
Accurate river discharge forecasting is critical for flood and drought management in deltaic regions vulnerable to climate extremes. This study evaluates one hyperparameter-optimized machine learning model (XGBoost) against five standard-configuration deep learning (DL) models (CNN, LSTM, GRU, CNN-GRU, LSTM+Attention) for daily discharge prediction in the Old Brahmaputra River. Using 22 years of data (2000–2021) from Mymensingh station, models were assessed across four lag-lead configurations (3-1, 3-3, 7-7, 10-10 days) using nine statistical metrics and PCA-based ranking with normalized composite scores. For 1-day predictions, LSTM+Attention achieved the highest composite score (0.7981), followed by CNN-GRU (0.7749), while all models exceeded R2 values of 0.98. CNN-GRU dominated 3-day forecasts with a composite score of 0.9390 (RMSE: 97.3199 m3/s, R2: 0.9498), and maintained competitive performance for 7-day predictions (R2: 0.8139). For 10-day forecasts, LSTM was superior with a 0.9115 composite score, yet the RMSE's sharp rise from 53.7469 (1-day) to 226.7971 m3/s highlights a significant accuracy loss with longer lead times. Performance degraded substantially with extended lead times, showing systematic underestimation of peak monsoon discharges. Results demonstrate that the DL models match or surpass optimized traditional approaches, with PCA rankings identifying optimal scenario-specific hierarchies for resource-constrained operational environments.Keywords
Funding Information
- University Grants Commission of Bangladesh (crop_science-16/2022-2023)
This publication has 37 references indexed in Scilit:
- Towards sustainability and circular economy: conceptual design model for the water-energy-food nexus in Ferdaws Village, Western Desert, EgyptInnovative Infrastructure Solutions, 2025
- River discharge prediction based multivariate climatological variables using hybridized long short-term memory with nature inspired algorithmJournal of Hydrology, 2024
- Hydro-informer: a deep learning model for accurate water level and flood predictionsNatural Hazards, 2024
- Ganges-Brahmaputra-Meghna River Delta2024
- Exploring the potential of deep learning for streamflow forecasting: A comparative study with hydrological models for seasonal and perennial riversExpert Systems with Applications, 2024
- Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023)Environmental Modelling & Software, 2024
- A review of hybrid deep learning applications for streamflow forecastingJournal of Hydrology, 2023
- Modeling metamorphosis of the Old Brahmaputra River and associated impacts on landscapes in the Central Bengal Basin, BangladeshInternational Journal of Earth Sciences, 2023
- Recent changes in ecosystem services and human well-being in the Bangladesh coastal zoneRegional Environmental Change, 2015
- Principal component analysisWIREs Computational Statistics, 2010