Integrating Process‐Based Reactive Transport Modeling and Machine Learning for Electrokinetic Remediation of Contaminated Groundwater

Abstract

Advanced reactive transport models of fluid flow and solute transport in subsurface porous media are instrumental for the assessment of contaminant environmental fate and for the design of in situ remediation interventions. However, the increasing complexity of process‐based reactive transport simulators often leads to long runtimes, which poses severe restrictions for tasks that require numerous model evaluations. To overcome this limitation, we demonstrate how machine learning surrogate models, trained on the outputs of a limited number of process‐based reactive transport simulations, can predict the evolution of complex subsurface systems. We focus on electrokinetic enhanced bioremediation of chlorinated solvents in low‐permeability porous media, which is an in situ remediation technology entailing a suite of complex and coupled physical, chemical, and biological processes. A process‐based, multicomponent reactive transport model, capable of describing the key mechanisms of electrokinetic flow and transport, is setup in a two‐dimensional domain. The model accounts for electromigration and electroosmosis, the electrostatic interactions between charged species, the chemistry of the pore water solution, the microbially mediated degradation of the organic compounds, and the dynamics of different degraders. We develop a response surface surrogate framework using an artificial neural network as approximation function and we show that the surrogate model has the capability and the flexibility to capture the complex dynamics of electrokinetic remediation in subsurface porous media and allows computationally efficient model exploration, sensitivity analysis, and uncertainty quantification.

A perspective on applied geochemistry in porous media: Reactive transport modeling of geochemical dynamics and the interplay with flow phenomena and physical alteration

“…Overall, to address the multiphysics and multi-scale challenges faced by many practical geochemical systems, smart modeling capability is needed, to be able to optimize local and global selection of the appropriate modeling approach, mesh resolution and time stepping. Meanwhile, machine learning algorithms have been increasingly used to bypass explicit description of (some of) these coupled processes (Mudunuru and Karra 2021;Sprocati and Rolle 2021;Prasianakis et al 2020;Leal et al 2020). While great potential has been recognized regarding the application of machine learning, especially with the advances in physics-informed algorithms, it is crucial to ensure continuous development of high-fidelity process-based models (D'Elia et al 2022).…”

A Review of In Situ Leaching (ISL) for Uranium Mining

“…Reactive transport models, in addition to their capability to predict production based on uranium deposit characteristics, are also employed for evaluating downgradient transport at in situ leaching sites. This aids in optimizing management decisions and facilitating groundwater remediation post-in situ leaching [162,163], contributing to maximizing returns and ensuring the sustainable development of uranium mining through in situ leaching.…”

A Critical Review of the Modelling Tools for the Reactive Transport of Organic Contaminants

“…In the context of the numerous studies on water quality, machine learning can predict the amount and fate of pollutants, taking into account complex processes and interactions between different control parameters. Particular attention is paid to organic pollutants and the assessment of contaminated sites, including through the application of image recognition technology [533][534][535][536][537][538][539].…”