Improving predictions of hydrological low-flow indices in ungaged basins using machine learning

Environmental Modelling and Software
By: , and 

Links

Abstract

We compare the ability of eight machine-learning models (elastic net, gradient boosting, kernel-k-nearest neighbors, two variants of support vector machines, M5-cubist, random forest, and a meta-learning ensemble M5-cubist model) and four baseline models (ordinary kriging, a unit area discharge model, and two variants of censored regression) to generate estimates of the annual minimum 7-day mean streamflow with an annual exceedance probability of 90% (7Q10) at 224 unregulated sites in South Carolina, Georgia, and Alabama, USA. The machine-learning models produced substantially lower cross validation errors compared to the baseline models. The meta-learning M5-cubist model had the lowest root-mean-squared-error of 26.72 cubic feet per second. Partial dependence plots show that 7Q10s are likely moderated by late summer and early fall precipitation and the infiltration capacity of basin soils.

Study Area

Additional publication details

Publication type Article
Publication Subtype Journal Article
Title Improving predictions of hydrological low-flow indices in ungaged basins using machine learning
Series title Environmental Modelling and Software
DOI 10.1016/j.envsoft.2017.12.021
Volume 101
Year Published 2018
Language English
Publisher Elsevier
Contributing office(s) Lower Mississippi-Gulf Water Science Center
Description 14 p.
First page 169
Last page 182
Country United States
State Alabama, Georgia, South Carolina