Including Physics in Deep Learning – An Example from 4D Seismic Pressure Saturation Inversion

J.S. Dramsch, G. Corte, H. Amini, C. Macbeth, M. Lüthje

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Geoscience data often have to rely on strong priors in the face of uncertainty. Additionally, we often try to detect or model anomalous sparse data that can appear as an outlier in machine learning models. These are classic examples of imbalanced learning. Approaching these problems can benefit from including prior information from physics models or transforming data to a beneficial domain. We show an example of including physical information in the architecture of a neural network as prior information. We go on to present noise injection at training time to successfully transfer the network from synthetic data to field data.
Original languageEnglish
Title of host publication81st EAGE Conference and Exhibition 2019 (Workshops)
PublisherEuropean Association of Geoscientists and Engineers
Publication date2019
Pages215-220
ISBN (Print)978-1-5108-9280-4
DOIs
Publication statusPublished - 2019
Event 81st EAGE Conference and Exhibition 2019 - ExCeL Centre, London, United Kingdom
Duration: 3 Jun 20196 Jun 2019
Conference number: 81

Conference

Conference 81st EAGE Conference and Exhibition 2019
Number81
LocationExCeL Centre
Country/TerritoryUnited Kingdom
CityLondon
Period03/06/201906/06/2019

Fingerprint

Dive into the research topics of 'Including Physics in Deep Learning – An Example from 4D Seismic Pressure Saturation Inversion'. Together they form a unique fingerprint.

Cite this