Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar

Common industry practice means that geological or stratigraphic boundaries are estimated from exploration drill holes. While exploration holes provide opportunities for accurate data at a high resolution down the hole, their acquisition is cost-intensive, which can result in the number of holes dril...

Full description

Bibliographic Details
Main Authors: Adrian Ball, Louisa O’Connor
Format: Article
Language:English
Published: MDPI AG 2021-07-01
Series:Geosciences
Subjects:
Online Access:https://www.mdpi.com/2076-3263/11/7/284
_version_ 1797527139394781184
author Adrian Ball
Louisa O’Connor
author_facet Adrian Ball
Louisa O’Connor
author_sort Adrian Ball
collection DOAJ
description Common industry practice means that geological or stratigraphic boundaries are estimated from exploration drill holes. While exploration holes provide opportunities for accurate data at a high resolution down the hole, their acquisition is cost-intensive, which can result in the number of holes drilled being reduced. In contrast, sampling with ground-penetrating radar (GPR) is cost-effective, non-destructive, and compact, allowing for denser, continuous data acquisition. One challenge with GPR data is the subjectivity and challenges associated with interpretation. This research presents a hybrid model of geologist and machine learning for the identification of geological boundaries in a lateritic deposit. This model allows for an auditable, probabilistic representation of geologists’ interpretations and can feed into exploration planning and optimising drill campaigns in terms of the density and location of holes.
first_indexed 2024-03-10T09:38:47Z
format Article
id doaj.art-fd0d7b9ec5814300888a21dd1145ea53
institution Directory Open Access Journal
issn 2076-3263
language English
last_indexed 2024-03-10T09:38:47Z
publishDate 2021-07-01
publisher MDPI AG
record_format Article
series Geosciences
spelling doaj.art-fd0d7b9ec5814300888a21dd1145ea532023-11-22T03:51:46ZengMDPI AGGeosciences2076-32632021-07-0111728410.3390/geosciences11070284Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating RadarAdrian Ball0Louisa O’Connor1Rio Tinto Centre for Mine Automation, The University of Sydney, Sydney 2006, AustraliaRio Tinto, Orebody Knowledge Centre of Excellence, Perth 6000, AustraliaCommon industry practice means that geological or stratigraphic boundaries are estimated from exploration drill holes. While exploration holes provide opportunities for accurate data at a high resolution down the hole, their acquisition is cost-intensive, which can result in the number of holes drilled being reduced. In contrast, sampling with ground-penetrating radar (GPR) is cost-effective, non-destructive, and compact, allowing for denser, continuous data acquisition. One challenge with GPR data is the subjectivity and challenges associated with interpretation. This research presents a hybrid model of geologist and machine learning for the identification of geological boundaries in a lateritic deposit. This model allows for an auditable, probabilistic representation of geologists’ interpretations and can feed into exploration planning and optimising drill campaigns in terms of the density and location of holes.https://www.mdpi.com/2076-3263/11/7/284ground-penetrating radarGaussian processesuncertainty modellinghybrid intelligenceoptimised exploration
spellingShingle Adrian Ball
Louisa O’Connor
Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
Geosciences
ground-penetrating radar
Gaussian processes
uncertainty modelling
hybrid intelligence
optimised exploration
title Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
title_full Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
title_fullStr Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
title_full_unstemmed Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
title_short Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar
title_sort geologist in the loop a hybrid intelligence model for identifying geological boundaries from augmented ground penetrating radar
topic ground-penetrating radar
Gaussian processes
uncertainty modelling
hybrid intelligence
optimised exploration
url https://www.mdpi.com/2076-3263/11/7/284
work_keys_str_mv AT adrianball geologistintheloopahybridintelligencemodelforidentifyinggeologicalboundariesfromaugmentedgroundpenetratingradar
AT louisaoconnor geologistintheloopahybridintelligencemodelforidentifyinggeologicalboundariesfromaugmentedgroundpenetratingradar