Automatic processing of time domain induced polarization data using supervised artificial neural networks
(2021) In Geophysical Journal International 224(1). p.312-325- Abstract
Processing of geophysical data is a time consuming task involving many different steps. One approach for accelerating and automating processing of geophysical data is to look towards machine learning (ML). ML encompasses a wide range of tools, which can be used to automate complicated and/or tedious tasks. We present strategies for automating the processing of time-domain induced polarization (IP) data using ML. An IP data set from Grindsted in Denmark is used to investigate the applicability of neural networks for processing such data. The Grindsted data set consists of eight profiles, with approximately 2000 data curves per profile, on average. Each curve needs to be processed, which, using the manual approach, can take 1-2 hr per... (More)
Processing of geophysical data is a time consuming task involving many different steps. One approach for accelerating and automating processing of geophysical data is to look towards machine learning (ML). ML encompasses a wide range of tools, which can be used to automate complicated and/or tedious tasks. We present strategies for automating the processing of time-domain induced polarization (IP) data using ML. An IP data set from Grindsted in Denmark is used to investigate the applicability of neural networks for processing such data. The Grindsted data set consists of eight profiles, with approximately 2000 data curves per profile, on average. Each curve needs to be processed, which, using the manual approach, can take 1-2 hr per profile. Around 20 per cent of the curves were manually processed and used to train and validate an artificial neural network. Once trained, the network could process all curves, in 6-15 s for each profile. The accuracy of the neural network, when considering the manual processing as a reference, is 90.8 per cent. At first, the network could not detect outlier curves, that is where entire chargeability curves were significantly different from their spatial neighbours. Therefore, an outlier curve detection algorithm was developed and implemented to work in tandem with the network. The automatic processing approach developed here, involving the neural network and the outlier curve detection, leads to similar inversion results as the manual processing, with the two significant advantages of reduced processing times and enhanced processing consistency.
(Less)
- author
- Barfod, Adrian S. ; Lévy, Leá LU and Larsen, Jakob Juul
- publishing date
- 2021-01-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Electrical resistivity tomography (ER6), Hydrogeophysics, Neural networks, fuzzy logic
- in
- Geophysical Journal International
- volume
- 224
- issue
- 1
- pages
- 14 pages
- publisher
- Oxford University Press
- external identifiers
-
- scopus:85096464787
- ISSN
- 0956-540X
- DOI
- 10.1093/gji/ggaa460
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2020 The Author(s). Published by Oxford University Press on behalf of The Royal Astronomical Society.
- id
- 826b0756-534f-4ab4-923e-a802f413c625
- date added to LUP
- 2021-12-14 11:55:01
- date last changed
- 2022-04-27 06:38:44
@article{826b0756-534f-4ab4-923e-a802f413c625,
abstract = {{<p>Processing of geophysical data is a time consuming task involving many different steps. One approach for accelerating and automating processing of geophysical data is to look towards machine learning (ML). ML encompasses a wide range of tools, which can be used to automate complicated and/or tedious tasks. We present strategies for automating the processing of time-domain induced polarization (IP) data using ML. An IP data set from Grindsted in Denmark is used to investigate the applicability of neural networks for processing such data. The Grindsted data set consists of eight profiles, with approximately 2000 data curves per profile, on average. Each curve needs to be processed, which, using the manual approach, can take 1-2 hr per profile. Around 20 per cent of the curves were manually processed and used to train and validate an artificial neural network. Once trained, the network could process all curves, in 6-15 s for each profile. The accuracy of the neural network, when considering the manual processing as a reference, is 90.8 per cent. At first, the network could not detect outlier curves, that is where entire chargeability curves were significantly different from their spatial neighbours. Therefore, an outlier curve detection algorithm was developed and implemented to work in tandem with the network. The automatic processing approach developed here, involving the neural network and the outlier curve detection, leads to similar inversion results as the manual processing, with the two significant advantages of reduced processing times and enhanced processing consistency. </p>}},
author = {{Barfod, Adrian S. and Lévy, Leá and Larsen, Jakob Juul}},
issn = {{0956-540X}},
keywords = {{Electrical resistivity tomography (ER6); Hydrogeophysics; Neural networks, fuzzy logic}},
language = {{eng}},
month = {{01}},
number = {{1}},
pages = {{312--325}},
publisher = {{Oxford University Press}},
series = {{Geophysical Journal International}},
title = {{Automatic processing of time domain induced polarization data using supervised artificial neural networks}},
url = {{http://dx.doi.org/10.1093/gji/ggaa460}},
doi = {{10.1093/gji/ggaa460}},
volume = {{224}},
year = {{2021}},
}