Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data

Jesper Sören Dramsch*, Gustavo Corte, Hamed Amini, Mikael Lüthje, Colin Macbeth

*Corresponding author for this work

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

Abstract

In this work we present a deep neural network inversion on map-based 4D seismic data for pressureand saturation. We present a novel neural network architecture that trains on synthetic data and pro-vides insights into observed field seismic. The network explicitly includes AVO gradient calculationwithin the network as physical knowledge to stabilize pressure and saturation changes separation. Weapply the method to Schiehallion field data and go on to compare the results to Bayesian inversionresults. Despite not using convolutional neural networks for spatial information, we produce mapswith good signal to noise ratio and coherency
Original languageEnglish
Title of host publicationProceedings of the Second EAGE Workshop Practical Reservoir Monitoring
Number of pages4
Publication date2019
DOIs
Publication statusPublished - 2019
EventSecond EAGE Workshop Practical Reservoir Monitoring - American Hotel, Amsterdam, Netherlands
Duration: 1 Apr 20194 Apr 2019

Conference

ConferenceSecond EAGE Workshop Practical Reservoir Monitoring
LocationAmerican Hotel
CountryNetherlands
CityAmsterdam
Period01/04/201904/04/2019

Keywords

  • 4D seismic
  • Deep learning
  • Geophysic
  • North Sea
  • Seismic inversion
  • Time-lapse
  • Pressure
  • Saturation

Fingerprint Dive into the research topics of 'Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data'. Together they form a unique fingerprint.

Cite this