Accelerating Reactive Transport Modeling: On-Demand Machine Learning Algorithm for Chemical Equilibrium Calculations

Leal, Allan; Kyas, Svetlana; Kulik, Dmitrii A.; Saar, Martin O.

doi:10.1007/s11242-020-01412-1

Cited by 43 publications

(79 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The chemical benchmark used throughout this work is inspired by Engesgaard and Kipp (1992) and is well known, with many variants, in the reactive transport community (e.g., Shao et al, 2009;Leal et al, 2020). It was chosen since it has been studied by many different authors and it is challenging enough from a computational point of view.…”

Section: The Chemical Benchmarkmentioning

confidence: 99%

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Lucia¹,

Kühn²

2021

Preprint

View full text Add to dashboard Cite

Abstract. The computational costs associated with coupled reactive transport simulations are mostly due to the chemical subsystem: replacing it with a pre-trained statistical surrogate is a promising strategy to achieve decisive speedups at the price of small accuracy losses and thus to extend the scale of problems which can be handled. We introduce a hierarchical coupling scheme in which full physics, equation-based geochemical simulations are partially replaced by surrogates. Errors on mass balance resulting from multivariate surrogate predictions effectively assess the accuracy of multivariate regressions at runtime: inaccurate surrogate predictions are rejected and the more expensive equation-based simulations are run instead. Gradient boosting regressors such as xgboost, not requiring data standardization and being able to handle Tweedie distributions, proved to be a suitable emulator. Finally, we devise a surrogate approach based on geochemical knowledge, which overcomes the issue of robustness when encountering previously unseen data, and which can serve as basis for further development of hybrid physics-AI modelling.

show abstract

Section: The Chemical Benchmarkmentioning

confidence: 99%

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

Lucia¹,

Kühn²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The need for dramatically improved prediction of river basin scale biogeochemical function is dramatic, but the computational challenges are daunting, But machine learning (ML) can play an important role in at least five ways: 1) ML can facilitate the inclusion of diverse big data in physics-based models for water and biogeochemistry through downscaling and upscaling approaches (Mital et al 2020;2021 submitted), 2) ML can achieve improved predictability by enabling calibration and validation of models for given river basins and watersheds (Cromwell et al 2021), 3) ML can enable the development of surrogate and reduced order/dimension models that capture watershed and river basin function with reduced computational expense, 4) On The Fly ML can be used for automation of uncertainty quantification (UQ) to choose dynamically the level of fidelity and computational expense that is adequate for a given river basin-scale simulation, and 5) On Demand ML can be used to gradually reduce the number of full predictive calculations that are needed to describe the watershed to river basin-scale biogeochemical function, essentially replacing full physics-based simulation with continuously improving surrogate models (Leal et al 2020).…”

Section: Narrativementioning

confidence: 99%

“…On Demand ML-based model fidelity selection: Considering biogeochemical processes in reactive transport simulations is computationally expensive. By using an on demand machine learning (ODML) algorithm (Leal et al 2020), however, the computing costs for biogeochemistry and transport calculations can be reduced by orders of magnitude. The ODML model will start with zero knowledge at the beginning of the simulation.…”

Section: Surrogate Models From Training On Synthetic High-resolution Datamentioning

confidence: 99%

On Demand Machine Learning for Multi-Fidelity Biogeochemistry in River Basins Impacted by Climate Extremes

Steefel

2021

View full text Add to dashboard Cite

Focal Area 2: Predictive modeling of watershed to river basin scale biogeochemistry through the use of AI techniques and AI-derived model components and the use of AI to design a prediction system comprised of a hierarchy of multi-fidelity models, including AI driven model/component/parameterization selection. Science Challenge: A full treatment of water flow and biogeochemical reactive transport at watershed to river basin scales is not currently possible, and yet there is a critical need to provide improved estimates of fluxes of nutrients and contaminants for both scientific and water management purposes at these scales. The use of hybrid multi-fidelity predictive models that take advantage of ML techniques offers an attractive option to overcome the obstacles associated with computational expense, especially insofar as it is possible to maintain process fidelity for heterogeneously distributed biogeochemical processes interacting with the hydrological cycle-a situation that is expected to be particularly pronounced during climate extremes.

show abstract

“…Recently, data‐driven approaches have gained momentum in watershed modeling because of their computational efficiency and agility to incorporate diverse and multiscale data that are often difficult to incorporate into current process‐based models (Shen, 2018). The value of ML for watershed modeling has been illustrated by applications focused on streamflow prediction (Kratzert, Klotz, Brenner, Schulz, & Herrnegger, 2018), early warning of droughts and floods (Mosavi, Ozturk, & Chau, 2018; Park, Im, Jang, & Rhee, 2016), groundwater level fluctuations (Müller et al, 2019), and chemical equilibrium calculations (Leal, Kulik, & Saar, 2017). However, as data‐driven models are developed directly from observations, their effectiveness is limited when data are sparse.…”

Section: Emerging Technologies Poised To Advance Watershed Hydrobiogementioning

confidence: 99%

Emerging technologies and radical collaboration to advance predictive understanding of watershed hydrobiogeochemistry

Hubbard

Varadharajan

et al. 2020

Hydrological Processes

View full text Add to dashboard Cite

Increasing population and resource-intensive lifestyles are driving enhanced demands for clean water, food, and energy. In parallel, landuse change, climate change, and perturbations-including drought, floods, fires, and early snowmelt-are significantly reshaping interactions within watersheds throughout the world. While watersheds are the Earth's key functional unit for assessing and managing water resources, hydrological processes in watersheds also mediate biogeochemical interactions that support terrestrial life on Earth (Kaushal, Gold, Bernal, & Tank, 2018; National Research Council, 2012). Although society is dependent upon clean water availability, tractable prediction of watershed hydrobiogeochemical behavior, including watershed response to perturbations, remains a challenge. Central to the challenge are complex, multiscale interactions between plants, microorganisms, organic matter, minerals, dissolved constituents, and migrating fluids, which occur within and across bedrock-to-canopy compartments and along extensive lateral gradients of a watershed. Several recent community reports have synthesized formidable challenges associated with watershed science and technology (AGU, 2018;Blöschl et al., 2019).Here, we discuss emerging technologies and collaboration modes that are critical for developing generalizable insights about and predictive understanding of complex watershed hydrobiogeochemical behavior, which are important for underpinning optimized natural resource management.Recent developments in field observatories and open-science principles provide foundational pillars for advancing predictive understanding of watershed hydrobiogeochemistry using emerging technologies. Field observatories have fostered crossdisciplinary collaboration and provided platforms for quantifying hydrological, biological, geological, geochemical, and atmospheric processes and their couplings (Bogena, White, Bour, Li, & Jensen, 2018). Observatory networks in the United States include the Critical Zone

show abstract

Accelerating Reactive Transport Modeling: On-Demand Machine Learning Algorithm for Chemical Equilibrium Calculations

Cited by 43 publications

References 66 publications

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

DecTree v1.0 – Chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates

On Demand Machine Learning for Multi-Fidelity Biogeochemistry in River Basins Impacted by Climate Extremes

Emerging technologies and radical collaboration to advance predictive understanding of watershed hydrobiogeochemistry

Contact Info

Product

Resources

About