Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Removal of Powerline Noise in Geophysical Datasets With a Scientific Machine-Learning Based Approach

Larsen, Jakob Juul ; Levy, Lea LU and Asif, Muhammad Rizwan LU (2022) In IEEE Transactions on Geoscience and Remote Sensing 60.
Abstract

The most common noise in geophysical data is probably interference from powerlines. This noise manifests itself as a sinusoidal signal oscillating at the fundamental 50 or 60 Hz frequency of the power grid and as harmonic components oscillating at integer multiples. Many different mitigation strategies, tailored for the specific geophysical method, have been developed to target powerline noise. One method that applies to fully sampled data is model-based subtraction, where a model of the powerline noise is fit to the noisy dataset and subsequently subtracted. In most cases, this leads to significant improvements in the signal-to-noise ratio. However, the determination of the powerline model parameters, in particular the fundamental... (More)

The most common noise in geophysical data is probably interference from powerlines. This noise manifests itself as a sinusoidal signal oscillating at the fundamental 50 or 60 Hz frequency of the power grid and as harmonic components oscillating at integer multiples. Many different mitigation strategies, tailored for the specific geophysical method, have been developed to target powerline noise. One method that applies to fully sampled data is model-based subtraction, where a model of the powerline noise is fit to the noisy dataset and subsequently subtracted. In most cases, this leads to significant improvements in the signal-to-noise ratio. However, the determination of the powerline model parameters, in particular the fundamental powerline frequency, is computationally expensive, as it requires repeated solutions of a least-squares problem. We demonstrate that the powerline frequency can be directly predicted with a scientific machine-learning-based approach. We work on both time domain-induced polarization and surface nuclear magnetic resonance data. We use a different network for each method to trade-off prediction accuracy and prediction speed. In both cases, the prediction accuracy is fully on par with standard methods, and we obtain speed-ups by factors of 400 and 10 for the two types of data.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Frequency prediction, geophysical datasets, powerline noise, scientific machine learning, surface nuclear magnetic resonance (NMR), time domain-induced polarization (TDIP)
in
IEEE Transactions on Geoscience and Remote Sensing
volume
60
article number
5923410
pages
10 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85144072853
ISSN
0196-2892
DOI
10.1109/TGRS.2022.3223737
language
English
LU publication?
yes
additional info
Publisher Copyright: © 1980-2012 IEEE.
id
69c6b40a-e037-40a3-9a25-8e2c5c90c403
date added to LUP
2022-12-28 12:25:16
date last changed
2023-11-07 01:17:34
@article{69c6b40a-e037-40a3-9a25-8e2c5c90c403,
  abstract     = {{<p>The most common noise in geophysical data is probably interference from powerlines. This noise manifests itself as a sinusoidal signal oscillating at the fundamental 50 or 60 Hz frequency of the power grid and as harmonic components oscillating at integer multiples. Many different mitigation strategies, tailored for the specific geophysical method, have been developed to target powerline noise. One method that applies to fully sampled data is model-based subtraction, where a model of the powerline noise is fit to the noisy dataset and subsequently subtracted. In most cases, this leads to significant improvements in the signal-to-noise ratio. However, the determination of the powerline model parameters, in particular the fundamental powerline frequency, is computationally expensive, as it requires repeated solutions of a least-squares problem. We demonstrate that the powerline frequency can be directly predicted with a scientific machine-learning-based approach. We work on both time domain-induced polarization and surface nuclear magnetic resonance data. We use a different network for each method to trade-off prediction accuracy and prediction speed. In both cases, the prediction accuracy is fully on par with standard methods, and we obtain speed-ups by factors of 400 and 10 for the two types of data.</p>}},
  author       = {{Larsen, Jakob Juul and Levy, Lea and Asif, Muhammad Rizwan}},
  issn         = {{0196-2892}},
  keywords     = {{Frequency prediction; geophysical datasets; powerline noise; scientific machine learning; surface nuclear magnetic resonance (NMR); time domain-induced polarization (TDIP)}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Geoscience and Remote Sensing}},
  title        = {{Removal of Powerline Noise in Geophysical Datasets With a Scientific Machine-Learning Based Approach}},
  url          = {{http://dx.doi.org/10.1109/TGRS.2022.3223737}},
  doi          = {{10.1109/TGRS.2022.3223737}},
  volume       = {{60}},
  year         = {{2022}},
}