Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty

We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have ava...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brown, Stephen, Rodi, William L, Seracini, Marco, Gu, Chen, Fehler, Michael, Faulds, James, Smith, Connor M, Treitel, Sven
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Brown, Stephen
Rodi, William L
Seracini, Marco
Gu, Chen
Fehler, Michael
Faulds, James
Smith, Connor M
Treitel, Sven
description We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have available a relatively small set of positive training sites (known resources or active power plants) and negative training sites (known drill sites with unsuitable geothermal conditions) and use these to constrain and optimize artificial neural networks for this classification task. The main objective is to predict the geothermal resource potential at unknown sites within a large geographic area where the defining features are known. These predictions could be used to target promising areas for further detailed investigations. We describe the evolution of our work from defining a specific neural network architecture to training and optimization trials. Upon analysis we expose the inevitable problems of model variability and resulting prediction uncertainty. Finally, to address these problems we apply the concept of Bayesian neural networks, a heuristic approach to regularization in network training, and make use of the practical interpretation of the formal uncertainty measures they provide.
doi_str_mv 10.48550/arxiv.2209.15543
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2209_15543</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2209_15543</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-b8c098e297a6f09e00975626bdfbe51ae782d34a08ac512e97af278384551c3</originalsourceid><addsrcrecordid>eNotj11LwzAYRnPjhUx_gFfLH2jNR9Om3s2hUxgqY4J35W36hgXXRpLM2X9vN7068PBw4BByw1leaKXYLYQf950LweqcK1XIS_JxDyNGBwN9wUOA_YR09OEzUusDXaFPOwz9tG8w-kMwSBcxYow9DumOvgXsnEnOD_To0o6-DwZDAjek8YpcWNhHvP7njGweH7bLp2z9unpeLtYZlJXMWm1YrVHUFZSW1chYXalSlG1nW1QcsNKikwUwDUZxgdPPikpLXSjFjZyR-Z_0HNZ8BddDGJtTYHMOlL_dbUxf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty</title><source>arXiv.org</source><creator>Brown, Stephen ; Rodi, William L ; Seracini, Marco ; Gu, Chen ; Fehler, Michael ; Faulds, James ; Smith, Connor M ; Treitel, Sven</creator><creatorcontrib>Brown, Stephen ; Rodi, William L ; Seracini, Marco ; Gu, Chen ; Fehler, Michael ; Faulds, James ; Smith, Connor M ; Treitel, Sven</creatorcontrib><description>We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have available a relatively small set of positive training sites (known resources or active power plants) and negative training sites (known drill sites with unsuitable geothermal conditions) and use these to constrain and optimize artificial neural networks for this classification task. The main objective is to predict the geothermal resource potential at unknown sites within a large geographic area where the defining features are known. These predictions could be used to target promising areas for further detailed investigations. We describe the evolution of our work from defining a specific neural network architecture to training and optimization trials. Upon analysis we expose the inevitable problems of model variability and resulting prediction uncertainty. Finally, to address these problems we apply the concept of Bayesian neural networks, a heuristic approach to regularization in network training, and make use of the practical interpretation of the formal uncertainty measures they provide.</description><identifier>DOI: 10.48550/arxiv.2209.15543</identifier><language>eng</language><subject>Computer Science - Learning ; Physics - Geophysics</subject><creationdate>2022-09</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2209.15543$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.15543$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Brown, Stephen</creatorcontrib><creatorcontrib>Rodi, William L</creatorcontrib><creatorcontrib>Seracini, Marco</creatorcontrib><creatorcontrib>Gu, Chen</creatorcontrib><creatorcontrib>Fehler, Michael</creatorcontrib><creatorcontrib>Faulds, James</creatorcontrib><creatorcontrib>Smith, Connor M</creatorcontrib><creatorcontrib>Treitel, Sven</creatorcontrib><title>Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty</title><description>We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have available a relatively small set of positive training sites (known resources or active power plants) and negative training sites (known drill sites with unsuitable geothermal conditions) and use these to constrain and optimize artificial neural networks for this classification task. The main objective is to predict the geothermal resource potential at unknown sites within a large geographic area where the defining features are known. These predictions could be used to target promising areas for further detailed investigations. We describe the evolution of our work from defining a specific neural network architecture to training and optimization trials. Upon analysis we expose the inevitable problems of model variability and resulting prediction uncertainty. Finally, to address these problems we apply the concept of Bayesian neural networks, a heuristic approach to regularization in network training, and make use of the practical interpretation of the formal uncertainty measures they provide.</description><subject>Computer Science - Learning</subject><subject>Physics - Geophysics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj11LwzAYRnPjhUx_gFfLH2jNR9Om3s2hUxgqY4J35W36hgXXRpLM2X9vN7068PBw4BByw1leaKXYLYQf950LweqcK1XIS_JxDyNGBwN9wUOA_YR09OEzUusDXaFPOwz9tG8w-kMwSBcxYow9DumOvgXsnEnOD_To0o6-DwZDAjek8YpcWNhHvP7njGweH7bLp2z9unpeLtYZlJXMWm1YrVHUFZSW1chYXalSlG1nW1QcsNKikwUwDUZxgdPPikpLXSjFjZyR-Z_0HNZ8BddDGJtTYHMOlL_dbUxf</recordid><startdate>20220930</startdate><enddate>20220930</enddate><creator>Brown, Stephen</creator><creator>Rodi, William L</creator><creator>Seracini, Marco</creator><creator>Gu, Chen</creator><creator>Fehler, Michael</creator><creator>Faulds, James</creator><creator>Smith, Connor M</creator><creator>Treitel, Sven</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220930</creationdate><title>Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty</title><author>Brown, Stephen ; Rodi, William L ; Seracini, Marco ; Gu, Chen ; Fehler, Michael ; Faulds, James ; Smith, Connor M ; Treitel, Sven</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-b8c098e297a6f09e00975626bdfbe51ae782d34a08ac512e97af278384551c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Physics - Geophysics</topic><toplevel>online_resources</toplevel><creatorcontrib>Brown, Stephen</creatorcontrib><creatorcontrib>Rodi, William L</creatorcontrib><creatorcontrib>Seracini, Marco</creatorcontrib><creatorcontrib>Gu, Chen</creatorcontrib><creatorcontrib>Fehler, Michael</creatorcontrib><creatorcontrib>Faulds, James</creatorcontrib><creatorcontrib>Smith, Connor M</creatorcontrib><creatorcontrib>Treitel, Sven</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Brown, Stephen</au><au>Rodi, William L</au><au>Seracini, Marco</au><au>Gu, Chen</au><au>Fehler, Michael</au><au>Faulds, James</au><au>Smith, Connor M</au><au>Treitel, Sven</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty</atitle><date>2022-09-30</date><risdate>2022</risdate><abstract>We consider the application of machine learning to the evaluation of geothermal resource potential. A supervised learning problem is defined where maps of 10 geological and geophysical features within the state of Nevada, USA are used to define geothermal potential across a broad region. We have available a relatively small set of positive training sites (known resources or active power plants) and negative training sites (known drill sites with unsuitable geothermal conditions) and use these to constrain and optimize artificial neural networks for this classification task. The main objective is to predict the geothermal resource potential at unknown sites within a large geographic area where the defining features are known. These predictions could be used to target promising areas for further detailed investigations. We describe the evolution of our work from defining a specific neural network architecture to training and optimization trials. Upon analysis we expose the inevitable problems of model variability and resulting prediction uncertainty. Finally, to address these problems we apply the concept of Bayesian neural networks, a heuristic approach to regularization in network training, and make use of the practical interpretation of the formal uncertainty measures they provide.</abstract><doi>10.48550/arxiv.2209.15543</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2209.15543
ispartof
issn
language eng
recordid cdi_arxiv_primary_2209_15543
source arXiv.org
subjects Computer Science - Learning
Physics - Geophysics
title Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T12%3A53%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Bayesian%20Neural%20Networks%20for%20Geothermal%20Resource%20Assessment:%20Prediction%20with%20Uncertainty&rft.au=Brown,%20Stephen&rft.date=2022-09-30&rft_id=info:doi/10.48550/arxiv.2209.15543&rft_dat=%3Carxiv_GOX%3E2209_15543%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true