Advanced machine learning techniques for daily streamflow forecasting: a case study of the Brahmaputra River
5 affiliations
- 1Department of Computer Science and Engineering, Military Institute of Science and Technology
- 2Faculty of Artificial Intelligence and Engineering, Multimedia University
- 3Department of Computer Science, College of Computing and Information Technology, Shaqra University
- 4Shiga University of Medical Science
- 5Department of Environmental Water Resources and Coastal Engineering, Military Institute of Science and Technology
Abstract
Accurate multi-day streamflow forecasts support flood preparedness, but single holdout scores can conceal lead-time dependence, temporal instability, baseline skill, and uncertainty. This study compares Long Short-Term Memory, Random Forest, Multiple Linear Regression, Multi-Layer Perceptron, Support Vector Regression, and AdaBoost using an audited Bangladesh Water Development Board discharge record for the Bahadurabad Transit station on the Brahmaputra River. The source contained 10,314 entries from 1995 to 2023. After 275 excess same-date records were consolidated by date-wise averaging, 553 calendar days were missing; no temporal interpolation was applied. We constructed 9,272 complete samples using 30 antecedent discharges to predict Days 1–30 directly. Leakage-resistant evaluation used three expanding rolling-origin folds, target-end-date training cut-offs, a 2019–2020 calibration period, and an independent 2021–2023 test period. Moving-block bootstrap confidence intervals, split-conformal prediction intervals, flow-regime errors, and lag sensitivity were evaluated. Random Forest had the lowest mean rolling-origin RMSE, whereas Multi-Layer Perceptron had the lowest pooled test RMSE (6,763.47 m³/s; R²/NSE = 0.721); their uncertainty intervals overlapped. Ranking changed with horizon: Multiple Linear Regression was best at Day 1 and AdaBoost at Day 30. All models underestimated the highest-flow decile. The results support an uncertainty-aware discharge-only benchmark, not universal model superiority or operational flood-warning readiness.
Related
- KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning
- XAI-driven analysis of influencing factors in streamflow-based flood forecasting via fine tuned MTV19Anet
- Hybrid machine learning framework for drought forecasting: integration of LSBoost, RQNN, CNN-RNN, CNN-LSTM and advanced data decomposition
- Towards generalized hydrological forecasting using transformer models for 120 h streamflow prediction
- Coupled Physics-Based and Machine Learning Streamflow Modeling with High-Resolution Flood Inundation and Impact Assessment for Hurricane Florence (2018): A Case Study of the Neuse River at Goldsboro, North Carolina
BibTeX
@article{siddiquee2026advanced,
title = {{Advanced machine learning techniques for daily streamflow forecasting: a case study of the Brahmaputra River}},
author = {Kazy Noor-e-Alam Siddiquee and Md Tanjil Sarker and Marran Al Qwaid and Nick Barua and Kazi Shamima Akter and Shohana Chowdhury and Md Sabbir Hossen and Md. Shabiul Islam},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-69747-1},
url = {https://doi.org/10.1038/s41598-026-69747-1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Advanced machine learning techniques for daily streamflow forecasting: a case study of the Brahmaputra River
AU - Kazy Noor-e-Alam Siddiquee
AU - Md Tanjil Sarker
AU - Marran Al Qwaid
AU - Nick Barua
AU - Kazi Shamima Akter
AU - Shohana Chowdhury
AU - Md Sabbir Hossen
AU - Md. Shabiul Islam
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-69747-1
UR - https://doi.org/10.1038/s41598-026-69747-1
AB - Accurate multi-day streamflow forecasts support flood preparedness, but single holdout scores can conceal lead-time dependence, temporal instability, baseline skill, and uncertainty. This study compares Long Short-Term Memory, Random Forest, Multiple Linear Regression, Multi-Layer Perceptron, Support Vector Regression, and AdaBoost using an audited Bangladesh Water Development Board discharge record for the Bahadurabad Transit station on the Brahmaputra River. The source contained 10,314 entries from 1995 to 2023. After 275 excess same-date records were consolidated by date-wise averaging, 553 calendar days were missing; no temporal interpolation was applied. We constructed 9,272 complete samples using 30 antecedent discharges to predict Days 1–30 directly. Leakage-resistant evaluation used three expanding rolling-origin folds, target-end-date training cut-offs, a 2019–2020 calibration period, and an independent 2021–2023 test period. Moving-block bootstrap confidence intervals, split-conformal prediction intervals, flow-regime errors, and lag sensitivity were evaluated. Random Forest had the lowest mean rolling-origin RMSE, whereas Multi-Layer Perceptron had the lowest pooled test RMSE (6,763.47 m³/s; R²/NSE = 0.721); their uncertainty intervals overlapped. Ranking changed with horizon: Multiple Linear Regression was best at Day 1 and AdaBoost at Day 30. All models underestimated the highest-flow decile. The results support an uncertainty-aware discharge-only benchmark, not universal model superiority or operational flood-warning readiness.
SN - 2045-2322
ER -