Surrogate playground

DOI

Surrogate playground is an automated machine learning approach written for rapidly screening a large number of different models to serve as surrogates for a slow running simulator. This code was written for a reactive transport application where a fluid flow model (hydrodynamics) is coupled to a geochemistry simulator (reactions in time and space) to simulate scenarios such as underground storage of CO2 or hydrogen storage for excess energy from wind farms. The challenge for such applications is that the geochemistry simulator is typically slow compared to fluid dynamics and constitutes the main bottleneck for producing highly detailed simulations of such application scenarios. This approach attempts to find machine learning models that can replace the slow running simulator when trained on input-output data from the geochemistry simulator. The code may be of more general interest as this prototype can be used to screen many different machine learning models for any regression problem in general. To illustrate this it also includes a demonstration example using the Boston housing standard data-set.

Identifier
DOI https://doi.org/10.5880/GFZ.1.5.2018.008
Related Identifier https://doi.org/10.1016/j.egypro.2016.10.047
Related Identifier https://gitext.gfz-potsdam.de/sec15pub/Surrogate_playground_core/tree/master
Metadata Access http://doidb.wdc-terra.org/oaip/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:doidb.wdc-terra.org:6725
Provenance
Creator Jatnieks, Janis; De Lucia, Marco ORCID logo; Sips, Mike ORCID logo; Dransch, Doris
Publisher GFZ Data Services
Publication Year 2019
Rights GNU Lesser General Public License v2.1; https://www.gnu.org/licenses/old-licenses/lgpl-2.1.en.html
OpenAccess true
Representation
Language English
Resource Type Software
Format application/octet-stream
Size 5 Files
Version 1.0
Discipline Geosciences