loading page

Quantifying Subsurface Parameter and Transport Uncertainty Using Surrogate Modeling and Environmental Tracers
  • +1
  • Nicholas Thiros,
  • W. Gardner,
  • Marco Maneta,
  • Douglas Brinkerhoff
Nicholas Thiros
University of Montana Missoula

Corresponding Author:nicholas.thiros@umontana.edu

Author Profile
W. Gardner
University of Montana
Author Profile
Marco Maneta
University of Montana
Author Profile
Douglas Brinkerhoff
University of Montana
Author Profile

Abstract

We combine physics-based groundwater reactive transport modeling with machine learning techniques to quantify hydrogeologic model and solute transport predictive uncertainties. We train an artificial neural network (ANN) on a dataset of groundwater hydraulic heads and 3H concentrations generated using a high-fidelity groundwater reactive transport model. Using the trained ANN as a surrogate model to reproduce the input-output response of the high-fidelity reactive transport model, we quantify the posterior distributions of hydrogeologic parameters and hydraulic forcing conditions using Markov-chain Monte Carlo (MCMC) calibration against field observations of groundwater hydraulic heads and 3H concentrations. We demonstrate the methodology with a model application that predicts Chlorofluorocarbon-12 (CFC-12) solute transport at a contaminated site in Wyoming, USA. Our results show that including 3H observations in the calibration dataset reduced the uncertainty in the estimated permeability field and infiltration rates, compared to calibration against hydraulic heads alone. However, predictive uncertainty quantification shows that CFC-12 transport predictions conditioned to the parameter posterior distributions cannot reproduce the field measurements. We found that calibrating the model to hydraulic head and 3H observations results in groundwater mean ages that are too large to explain the observed CFC-12 concentrations. The coupling of the physics-based reactive transport model with the machine learning surrogate model allows us to efficiently quantify model parameter and predictive uncertainties, which is typically computationally intractable using reactive transport models alone.
02 Sep 2021Submitted to Hydrological Processes
06 Sep 2021Submission Checks Completed
06 Sep 2021Assigned to Editor
08 Sep 2021Reviewer(s) Assigned
21 Sep 2022Review(s) Completed, Editorial Evaluation Pending
11 Oct 20221st Revision Received
12 Oct 2022Submission Checks Completed
12 Oct 2022Assigned to Editor
12 Oct 2022Reviewer(s) Assigned
12 Oct 2022Review(s) Completed, Editorial Evaluation Pending
12 Oct 2022Editorial Decision: Accept
17 Oct 2022Published in Hydrological Processes. 10.1002/hyp.14743