Optimizing groundwater remediation designs under uncertainty using dynamic surrogate models

Shengquan Yan, Barbara Minsker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computational cost is a critical issue for large-scale water resource optimization problems that often involve time-consuming simulation models. This issue is compounded when optimizing under uncertainty, since Monte Carlo simulations are often required to evaluate objective function values over multiple parameter realizations. In order to improve computational efficiency, we propose a dynamic surrogate modeling approach to approximate and replace the time-consuming numerical models within a noisy genetic algorithm (GA) optimization framework. The surrogates are trained to predict the distribution of the objectives online, using Monte Carlo simulation results created during the GA run. The surrogates are then adaptively updated to improve their prediction performance and correct the GA's convergence as the search progresses. Latin Hypercube sampling method is used to efficiently sample parameters for the Monte Carlo simulation and the sampling results are archived so that the estimation of the objective function distributions is progressively improved. The GA is modified to incorporate hypothesis tests to produce reliable solutions. The method is applied to a hypothetical groundwater remediation design case study, where the primary source of uncertainty stems from hydraulic conductivity values in the aquifers. Our preliminary results show that the technique can lead to reliable and cost-effective solutions with significantly less computational effort.

Original languageEnglish (US)
Title of host publicationExamining the Confluence of Environmental and Water Concerns - Proceedings of the World Environmental and Water Resources Congress 2006
DOIs
StatePublished - Dec 1 2007
EventWorld Environmental and Water Resources Congress 2006: Examining the Confluence of Environmental and Water Concerns - Omaha, NE, United States
Duration: May 21 2006May 25 2006

Publication series

NameExamining the Confluence of Environmental and Water Concerns - Proceedings of the World Environmental and Water Resources Congress 2006

Other

OtherWorld Environmental and Water Resources Congress 2006: Examining the Confluence of Environmental and Water Concerns
CountryUnited States
CityOmaha, NE
Period5/21/065/25/06

Keywords

  • Ground-water management
  • Optimization
  • Remedial action
  • Uncertainty principles

ASJC Scopus subject areas

  • Environmental Science(all)

Fingerprint Dive into the research topics of 'Optimizing groundwater remediation designs under uncertainty using dynamic surrogate models'. Together they form a unique fingerprint.

  • Cite this

    Yan, S., & Minsker, B. (2007). Optimizing groundwater remediation designs under uncertainty using dynamic surrogate models. In Examining the Confluence of Environmental and Water Concerns - Proceedings of the World Environmental and Water Resources Congress 2006 [137] (Examining the Confluence of Environmental and Water Concerns - Proceedings of the World Environmental and Water Resources Congress 2006). https://doi.org/10.1061/40856(200)137