{"title":"Inversion of DC Resistivity Data using Physics-Informed Neural Networks","authors":"Rohan Sharma, Divakar Vashisth, Kuldeep Sarkar, Upendra Kumar Singh","doi":"arxiv-2408.02420","DOIUrl":null,"url":null,"abstract":"The inversion of DC resistivity data is a widely employed method for\nnear-surface characterization. Recently, deep learning-based inversion\ntechniques have garnered significant attention due to their capability to\nelucidate intricate non-linear relationships between geophysical data and model\nparameters. Nevertheless, these methods face challenges such as limited\ntraining data availability and the generation of geologically inconsistent\nsolutions. These concerns can be mitigated through the integration of a\nphysics-informed approach. Moreover, the quantification of prediction\nuncertainty is crucial yet often overlooked in deep learning-based inversion\nmethodologies. In this study, we utilized Convolutional Neural Networks (CNNs)\nbased Physics-Informed Neural Networks (PINNs) to invert both synthetic and\nfield Schlumberger sounding data while also estimating prediction uncertainty\nvia Monte Carlo dropout. For both synthetic and field case studies, the median\nprofile estimated by PINNs is comparable to the results from existing\nliterature, while also providing uncertainty estimates. Therefore, PINNs\ndemonstrate significant potential for broader applications in near-surface\ncharacterization.","PeriodicalId":501270,"journal":{"name":"arXiv - PHYS - Geophysics","volume":"11 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Geophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.02420","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The inversion of DC resistivity data is a widely employed method for
near-surface characterization. Recently, deep learning-based inversion
techniques have garnered significant attention due to their capability to
elucidate intricate non-linear relationships between geophysical data and model
parameters. Nevertheless, these methods face challenges such as limited
training data availability and the generation of geologically inconsistent
solutions. These concerns can be mitigated through the integration of a
physics-informed approach. Moreover, the quantification of prediction
uncertainty is crucial yet often overlooked in deep learning-based inversion
methodologies. In this study, we utilized Convolutional Neural Networks (CNNs)
based Physics-Informed Neural Networks (PINNs) to invert both synthetic and
field Schlumberger sounding data while also estimating prediction uncertainty
via Monte Carlo dropout. For both synthetic and field case studies, the median
profile estimated by PINNs is comparable to the results from existing
literature, while also providing uncertainty estimates. Therefore, PINNs
demonstrate significant potential for broader applications in near-surface
characterization.