Projekter pr. år
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 modelbased 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 signaltonoise 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 leastsquares problem. We demonstrate that the powerline frequency can be directly predicted with a scientific machinelearningbased approach. We work on both time domaininduced polarization and surface nuclear magnetic resonance data. We use a different network for each method to tradeoff prediction accuracy and prediction speed. In both cases, the prediction accuracy is fully on par with standard methods, and we obtain speedups by factors of 400 and 10 for the two types of data.
Originalsprog  Engelsk 

Artikelnummer  5923410 
Tidsskrift  IEEE Transactions on Geoscience and Remote Sensing 
Vol/bind  60 
Antal sider  10 
ISSN  01962892 
DOI  
Status  Udgivet  2022 
Fingeraftryk
Dyk ned i forskningsemnerne om 'Removal of powerline noise in geophysical data sets with a scientific machinelearning based approach'. Sammen danner de et unikt fingeraftryk.Projekter
 2 Afsluttet

Flood and Drought – Tracking water in the shallow subsurface
01/10/2019 → 30/09/2023
Projekter: Projekt › Forskning

GIRem: Guided Injection Remediation (GIRem )
Christiansen, A. V. (PI), Larsen, J. J. (PI), Maurya, P. K. (Deltager), Liu, L. (Deltager), Domenzain Gonzalez, D. (Deltager), Kühl, A. K. (Deltager), Meldgaard Madsen, L. (Deltager), Barfod, A. (Deltager), Nielsen, A. N. (Deltager), Auken, E. (Deltager) & Dalsgaard, K. E. (Deltager)
01/07/2018 → 31/12/2022
Projekter: Projekt › Forskning