Integrating surrogate models into subsurface simulation framework allows 
computation of complex reactive transport scenarios

De Lucia, M.; Kempka, T.; Jatnieks, Janis; Kühn, M.

doi:10.1016/j.egypro.2017.08.200

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Integrating surrogate models into subsurface simulation framework allows computation of complex reactive transport scenarios

Authors

/persons/resource/delucia

De Lucia, M.
3.4 Fluid Systems Modelling, 3.0 Geochemistry, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/kempka

Kempka, T.
3.4 Fluid Systems Modelling, 3.0 Geochemistry, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/janisj

Jatnieks, Janis
1.5 Geoinformatics, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/mkuehn

Kühn, M.
3.4 Fluid Systems Modelling, 3.0 Geochemistry, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

External Ressource

No external resources are shared

Fulltext (public)

2566896.pdf
(Publisher version), 2MB

Supplementary Material (public)

There is no public supplementary material available

Citation

De Lucia, M., Kempka, T., Jatnieks, J., Kühn, M. (2017): Integrating surrogate models into subsurface simulation framework allows computation of complex reactive transport scenarios. - Energy Procedia, 125, 580-587.
https://doi.org/10.1016/j.egypro.2017.08.200

Cite as: https://gfzpublic.gfz-potsdam.de/pubman/item/item_2566896

Abstract

We showcase a flexible, extensible yet efficient framework for reactive transport modelling, including the ability to replace “full physics” geochemical simulations with surrogate models for speedup. Surrogates are data-driven models trained on a set of pre-calculated simulations by means of machine-learning methods. We offer also an input-output-error visualization component for interactive assessment and tuning of their accuracy. Our framework, based on open source or freely available software, makes possible complex reactive transport simulations and ease further research on optimized algorithms to tackle many geoscientific problems.