Abstract
A novel method for permeability prediction is presented using multivariant structural regression. A machine learning based model is trained using a large number (2,190, extrapolated to 219,000) of synthetic datasets constructed using a variety of object-based techniques. Permeability, calculated on each of these networks using traditional digital rock approaches, was used as a target function for a multivariant description of the pore network structure, created from the statistics of a discrete description of grains, pores and throats, generated through image analysis. A regression model was created using an Extra-Trees method with an error of <4% on the target set. This model was then validated using a composite series of data created both from proprietary datasets of carbonate and sandstone samples and open source data available from the Digital Rocks Portal (www.digitalrocksporta.org) with a Root Mean Square Fractional Error of <25%. Such an approach has wide applicability to problems of heterogeneity and scale in pore scale analysis of porous media, particularly as it has the potential of being applicable on 2D as well as 3D data.
Highlights
Flow and transport in porous media are fundamentally rooted at the scale of the tiny tortuous pore pathways through which the flow takes place
Traditional approaches to the prediction of effective properties from porous media focus on coupling the 3D structural imaging of porous media with the full physical simulation of the partial differential equations governing the property of interest [13], [18]
Such an approach is contrasted to more traditional approaches for effective property estimation, such as Kozeny-Carman or Kuwabara [19], [20] techniques which feed a relatively limited and difficult to measure set of structural properties into quasi-analytical models to make flow estimations
Summary
Flow and transport in porous media are fundamentally rooted at the scale of the tiny tortuous pore pathways through which the flow takes place. Pore scale investigation is a widely adopted tool across a range of disciplines associated with the examination of flow and transport Such an approach has applications ranging from understanding the flow properties of porous ceramics (used as a catalytic substrate for vehicle emission reduction) [1], [2], examining battery electrolyte exchange [3], [4], characterizing geological formations for the purpose of understanding groundwater flow [5], carbon capture and storage [6]–[8] and (in its most industrially applied application) oil and gas recovery [9]– [12]. Once the domain and physics have been defined (with appropriate boundary conditions), the physics converges over multiple iterations Such an approach is contrasted to more traditional (legacy) approaches for effective property estimation, such as Kozeny-Carman or Kuwabara [19], [20] techniques which feed a relatively limited and difficult to measure set of structural properties into quasi-analytical models to make flow estimations. These are typically inaccurate (e.g. [21]), may require
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
