Interpretable monthly streamflow estimation for seasonal water-resource management in highland watershed
Water Science · 29.10.2026 · 40 (1)
DOI: 10.1007/s44533-026-00087-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water Science, online erschienen am 29.10.2026. Verfasst von Anh The Pham und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Monthly streamflow information supports seasonal water-resource planning in tropical highland basins, where dry-season scarcity and wet-season runoff require different management responses. This study evaluated an integrated hydrological machine-learning and socio-economic water-pressure screening framework (Hydro-ML–SEWP) for the Da Tam watershed, Lam Dong Province, Vietnam. The hydrological models estimate monthly discharge conditionally on target-month rainfall and temperature together with antecedent streamflow, lagged rainfall, rolling hydroclimatic indicators, and seasonal cyclic terms; they are therefore within-month estimators rather than strict lead-time forecasts. A seasonal-naive benchmark, Ridge regression, support vector regression with a radial basis function kernel (SVR-RBF), Random Forest, and Gradient Boosting were assessed using a chronological 2019–2024 hold-out period and rolling-origin evaluation for 2011–2024. Ridge regression gave the highest R2 and lowest RMSE in both evaluations (hold-out R2 = 0.863, RMSE = 0.904 m3 s−1; rolling-origin R2 = 0.831, RMSE = 1.047 m3 s−1), whereas Random Forest gave the lowest MAE and the highest normalized composite score. Target-month rainfall, seasonal cyclicity, 1-month lagged discharge, and 1-month lagged rainfall represented 77.1% of the Random Forest impurity-based importance, although correlated predictors and the use of concurrent rainfall limit causal interpretation. Screening of the 1995–2024 drainage-area-transferred streamflow series identified February–March and September–October as the principal low-flow and high-flow periods. Because the source dataset does not identify the reference gauge and the available socio-economic records are not temporally aligned across all four proposed SEWP components, absolute discharge magnitudes and annual SEWP values are not treated as fully verified basin-specific quantities. The framework is therefore presented as a transparent conditional-estimation and scenario-screening approach whose operational use requires documented reference-basin metadata, target-month meteorological forecasts or lag-only predictors, and watershed-scale socio-economic data.
Zitieren
APA
Pham, A. T., Truong, C. T., Bui, A. X., & Tran, B. Q. (2026). Interpretable monthly streamflow estimation for seasonal water-resource management in highland watershed. Water Science, 40(1). https://doi.org/10.1007/s44533-026-00087-9
Vancouver
Pham AT, Truong CT, Bui AX, Tran BQ. Interpretable monthly streamflow estimation for seasonal water-resource management in highland watershed. Water Science. 2026;40(1). doi:10.1007/s44533-026-00087-9
BibTeX
@article{Pham2026,
author = {Pham, Anh The and Truong, Canh Thanh and Bui, An Xuan and Tran, Bao Quoc},
title = {Interpretable monthly streamflow estimation for seasonal water-resource management in highland watershed},
journal = {Water Science},
year = {2026},
volume = {40},
number = {1},
doi = {10.1007/s44533-026-00087-9}
}
EUVIMED