Machine learning methods for reservoir prediction modelling under uncertainty: Tackling multiples scales

Research output: Contribution to conferencePaper

Abstract

Reservoir prediction modelling conventionally involves complex statistical models that aim to integrate feature on multiple scales. These features are sourced from various types of data and often have a significant impact on flow performance. Conventional geostatistical algorithms provide a framework to integrate data from different scales, such as: geological interpretation of depositional structure based on analogues (e.g. by using conceptual training images); spatial correlation of geological bodies, their variety and geometrical relations (e.g. with imbedded geometrical shapes or elicited relations from analogues); high resolution seismic can be a source of multi-scale model features that can be integrated into stochastic model by means of soft conditioning.
Original languageEnglish
Pages1-2
Number of pages2
DOIs
Publication statusPublished - Jun 2014
Event76th EAGE Conference and Exhibition 2014 - Amsterdam, Netherlands
Duration: 16 Jun 201419 Jun 2014

Conference

Conference76th EAGE Conference and Exhibition 2014
CountryNetherlands
CityAmsterdam
Period16/06/1419/06/14

Fingerprint Dive into the research topics of 'Machine learning methods for reservoir prediction modelling under uncertainty: Tackling multiples scales'. Together they form a unique fingerprint.

  • Cite this