AnnRG - An artificial neural network solute geothermometer ...
Solute artificial neural network geothermometers offer the possibility to overcome the complexity given by the solute-mineral composition. Herein, we present a new concept, trained from high-quality hydrochemical data and verified by in-situ temperature measurements with a total of 208 data pairs of...
Main Authors: | , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
Elsevier
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.5445/ir/1000164573 https://publikationen.bibliothek.kit.edu/1000164573 |
id |
ftdatacite:10.5445/ir/1000164573 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.5445/ir/1000164573 2023-12-31T10:08:18+01:00 AnnRG - An artificial neural network solute geothermometer ... Ystroem, Lars H. Vollmer, Mark Kohl, Thomas Nitschke, Fabian 2023 https://dx.doi.org/10.5445/ir/1000164573 https://publikationen.bibliothek.kit.edu/1000164573 en eng Elsevier Creative Commons Namensnennung 4.0 International Open Access info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/deed.de AnnRG Machine learning Artificial neural network Solute geothermometry Geochemical exploration Reservoir temperature prediction ScholarlyArticle article-journal Journal Article Text 2023 ftdatacite https://doi.org/10.5445/ir/1000164573 2023-12-01T11:24:12Z Solute artificial neural network geothermometers offer the possibility to overcome the complexity given by the solute-mineral composition. Herein, we present a new concept, trained from high-quality hydrochemical data and verified by in-situ temperature measurements with a total of 208 data pairs of geochemical input parameters (Na+, K+, Ca2+, Mg2+, Cl−, SiO2, and pH) and reservoir temperature measurements being compiled. The data comprises nine geothermal sites with a broad variety of geochemical characteristics and enthalpies. Five sites with 163 samples (Upper Rhine Graben, Pannonian Basin, German Molasse Basin, Paris Basin, and Iceland) are used to develop the ANN geothermometer, while further four sites with 45 samples (Azores, El Tatio, Miavalles, and Rotorua) are used to encounter the established artificial neural network in practice to unknown data. The setup of the application, as well as the optimisation of the network architecture and its hyperparameters, are stepwise introduced. As a result, the ... Text Iceland DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
English |
topic |
AnnRG Machine learning Artificial neural network Solute geothermometry Geochemical exploration Reservoir temperature prediction |
spellingShingle |
AnnRG Machine learning Artificial neural network Solute geothermometry Geochemical exploration Reservoir temperature prediction Ystroem, Lars H. Vollmer, Mark Kohl, Thomas Nitschke, Fabian AnnRG - An artificial neural network solute geothermometer ... |
topic_facet |
AnnRG Machine learning Artificial neural network Solute geothermometry Geochemical exploration Reservoir temperature prediction |
description |
Solute artificial neural network geothermometers offer the possibility to overcome the complexity given by the solute-mineral composition. Herein, we present a new concept, trained from high-quality hydrochemical data and verified by in-situ temperature measurements with a total of 208 data pairs of geochemical input parameters (Na+, K+, Ca2+, Mg2+, Cl−, SiO2, and pH) and reservoir temperature measurements being compiled. The data comprises nine geothermal sites with a broad variety of geochemical characteristics and enthalpies. Five sites with 163 samples (Upper Rhine Graben, Pannonian Basin, German Molasse Basin, Paris Basin, and Iceland) are used to develop the ANN geothermometer, while further four sites with 45 samples (Azores, El Tatio, Miavalles, and Rotorua) are used to encounter the established artificial neural network in practice to unknown data. The setup of the application, as well as the optimisation of the network architecture and its hyperparameters, are stepwise introduced. As a result, the ... |
format |
Text |
author |
Ystroem, Lars H. Vollmer, Mark Kohl, Thomas Nitschke, Fabian |
author_facet |
Ystroem, Lars H. Vollmer, Mark Kohl, Thomas Nitschke, Fabian |
author_sort |
Ystroem, Lars H. |
title |
AnnRG - An artificial neural network solute geothermometer ... |
title_short |
AnnRG - An artificial neural network solute geothermometer ... |
title_full |
AnnRG - An artificial neural network solute geothermometer ... |
title_fullStr |
AnnRG - An artificial neural network solute geothermometer ... |
title_full_unstemmed |
AnnRG - An artificial neural network solute geothermometer ... |
title_sort |
annrg - an artificial neural network solute geothermometer ... |
publisher |
Elsevier |
publishDate |
2023 |
url |
https://dx.doi.org/10.5445/ir/1000164573 https://publikationen.bibliothek.kit.edu/1000164573 |
genre |
Iceland |
genre_facet |
Iceland |
op_rights |
Creative Commons Namensnennung 4.0 International Open Access info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/deed.de |
op_doi |
https://doi.org/10.5445/ir/1000164573 |
_version_ |
1786840987647082496 |