thumbnail

NWTOPT — A hyperparameter optimization approach for selection of environmental model solver settings

Environmental Modelling and Software
By:  and 
https://doi.org/10.1016/j.envsoft.2021.105250

Metrics

8
Crossref references
Web analytics dashboard Metrics definitions

Links

Abstract

Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is described that uses Tree of Parzen Estimators (TPE) and Random Search algorithms to optimize MODFLOW-NWTs solver settings. We ran 3500 trials on a steady-state and transient model. To quantify the performance of candidate solver settings, we defined a loss function based on time elapsed and mass balance error of the MODFLOW-NWT forward run. Before optimization the steady- state model ran in ~12 min and the transient model ran in ~5 h with acceptable mass balance error (<1%). After optimization runtimes were reduced to ~2.7 min (steady state) and ~48 min (transient) with errors below 0.1%. In both cases TPE found hyperparameters that resulted in faster running and lower error models than those found by Random Search. The time to complete the optimization trials was also shorter with the TPE algorithm.

Suggested Citation

Newcomer, M.W., and Hunt, R., 2022, NWTOPT — A hyperparameter optimization approach for selection of environmental model solver settings: Environmental Modelling and Software, v. 147, p. 1-7, https://doi.org/10.1016/j.envsoft.2021.105250.

Publication type Article
Publication Subtype Journal Article
Title NWTOPT — A hyperparameter optimization approach for selection of environmental model solver settings
Series title Environmental Modelling and Software
DOI 10.1016/j.envsoft.2021.105250
Volume 147
Year Published 2022
Language English
Publisher Elsevier
Contributing office(s) Upper Midwest Water Science Center
Description 105250, 7 p.
First page 1
Last page 7
Additional publication details