Machine learning enhancement of thermal response tests for geothermal potential evaluations at site and regional scales

Paul Bourhis; Benoît Cousin; Alessandro F. Rotta Loria; Lyesse Laloui

doi:10.1016/j.geothermics.2021.102132

Machine learning enhancement of thermal response tests for geothermal potential evaluations at site and regional scales

Paul Bourhis, Benoît Cousin^*, Alessandro F. Rotta Loria, Lyesse Laloui

^*Corresponding author for this work

Civil and Environmental Engineering

Research output: Contribution to journal › Article › peer-review

25 Scopus citations

Abstract

This study explores and validates a machine learning approach for the practical, effective, and precise prediction of the thermo-physical characteristics that are essential for the analysis and design of shallow geothermal systems, including borehole heat exchangers: (i) undisturbed ground temperature, (ii) ground effective thermal conductivity, and (iii) borehole thermal resistance. Benefiting from 174 thermal response tests from central and western Switzerland, the algorithm is used to provide accurate site-specific as well as regional-scale predictions of the investigated thermo-physical characteristics, which in turn can serve preliminary yet representative evaluations of the geothermal potential of even very broad areas.

Original language	English (US)
Article number	102132
Journal	Geothermics
Volume	95
DOIs	https://doi.org/10.1016/j.geothermics.2021.102132
State	Published - Sep 2021

Funding

This work was supported by the Swiss National Science Foundation (grant number 40B1-0_189766 ) and was possible thanks to the TRT data made available by the State of Vaud (DGE/GEODE), Geoazimut and Geotest.

Keywords

Borehole heat exchangers
Data-driven predictions
Geothermal energy
Machine learning
Thermal response testing

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Geotechnical Engineering and Engineering Geology
Geology

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.geothermics.2021.102132

Cite this

@article{51099eb8c2bb47cf804d8a5126af4010,

title = "Machine learning enhancement of thermal response tests for geothermal potential evaluations at site and regional scales",

abstract = "This study explores and validates a machine learning approach for the practical, effective, and precise prediction of the thermo-physical characteristics that are essential for the analysis and design of shallow geothermal systems, including borehole heat exchangers: (i) undisturbed ground temperature, (ii) ground effective thermal conductivity, and (iii) borehole thermal resistance. Benefiting from 174 thermal response tests from central and western Switzerland, the algorithm is used to provide accurate site-specific as well as regional-scale predictions of the investigated thermo-physical characteristics, which in turn can serve preliminary yet representative evaluations of the geothermal potential of even very broad areas.",

keywords = "Borehole heat exchangers, Data-driven predictions, Geothermal energy, Machine learning, Thermal response testing",

author = "Paul Bourhis and Beno{\^i}t Cousin and {Rotta Loria}, {Alessandro F.} and Lyesse Laloui",

note = "Publisher Copyright: {\textcopyright} 2021",

year = "2021",

month = sep,

doi = "10.1016/j.geothermics.2021.102132",

language = "English (US)",

volume = "95",

journal = "Geothermics",

issn = "0375-6505",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Machine learning enhancement of thermal response tests for geothermal potential evaluations at site and regional scales

AU - Bourhis, Paul

AU - Cousin, Benoît

AU - Rotta Loria, Alessandro F.

AU - Laloui, Lyesse

PY - 2021/9

Y1 - 2021/9

N2 - This study explores and validates a machine learning approach for the practical, effective, and precise prediction of the thermo-physical characteristics that are essential for the analysis and design of shallow geothermal systems, including borehole heat exchangers: (i) undisturbed ground temperature, (ii) ground effective thermal conductivity, and (iii) borehole thermal resistance. Benefiting from 174 thermal response tests from central and western Switzerland, the algorithm is used to provide accurate site-specific as well as regional-scale predictions of the investigated thermo-physical characteristics, which in turn can serve preliminary yet representative evaluations of the geothermal potential of even very broad areas.

AB - This study explores and validates a machine learning approach for the practical, effective, and precise prediction of the thermo-physical characteristics that are essential for the analysis and design of shallow geothermal systems, including borehole heat exchangers: (i) undisturbed ground temperature, (ii) ground effective thermal conductivity, and (iii) borehole thermal resistance. Benefiting from 174 thermal response tests from central and western Switzerland, the algorithm is used to provide accurate site-specific as well as regional-scale predictions of the investigated thermo-physical characteristics, which in turn can serve preliminary yet representative evaluations of the geothermal potential of even very broad areas.

KW - Borehole heat exchangers

KW - Data-driven predictions

KW - Geothermal energy

KW - Machine learning

KW - Thermal response testing

UR - http://www.scopus.com/inward/record.url?scp=85107629944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107629944&partnerID=8YFLogxK

U2 - 10.1016/j.geothermics.2021.102132

DO - 10.1016/j.geothermics.2021.102132

M3 - Article

AN - SCOPUS:85107629944

SN - 0375-6505

VL - 95

JO - Geothermics

JF - Geothermics

M1 - 102132

ER -

Machine learning enhancement of thermal response tests for geothermal potential evaluations at site and regional scales

Abstract

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this