CoreScore: an ML approach to assess legacy core condition

Fellgett, Mark; Hall, Alex; Harris, Simon; Damaschke, Magret; Kingdon, Andrew ORCID: https://orcid.org/0000-0003-4979-588X. 2023 CoreScore: an ML approach to assess legacy core condition. In: Neal, A.; Ashton, M.; Williams, L.S.; Dee, S.J.; Dodd, T.J.H.; Marshall, J.D., (eds.) Core Values: the Role of Core in Twenty-first Century Reservoir Characterization. Geological Society of London, 137-151. (Geological Society Special Publication, 527, 527).

Before downloading, please read NORA policies.

Preview

Text (Open Access Paper)
fellgett-et-al-2023-corescore-a-machine-learning-approach-to-assess-legacy-core-condition.pdf - Published Version
Available under License Creative Commons Attribution 4.0.
Download (6MB) | Preview

Official URL: http://dx.doi.org/10.1144/SP527-2021-200

Abstract/Summary

Today's geoscience challenges often require repurposing of data and samples from legacy boreholes. Collection of new deep core is expensive; maximising this investment is vital. However, condition of legacy cores varies due to factors including recovery, sampling, lithology, and storage. Rock Quality Designation analysis is often undertaken on new core but this only provides a snapshot of core condition and will not be indicative of subsequent condition. Poor core condition can make destructive analytical techniques impossible and also impacts non-destructive techniques including core scanning. Since 2011, BGS have systematically collected 125,000 core images. This study investigates if core condition of this archive can be assessed using automated analysis by machine learning. A neural network-based approach was used to segment these images. By differentiating imaged core from their background, properties such as number of fragments and total rock area were determined and used to assess core condition. Analysis of outputs demonstrate that with minimal input data, core condition can be rapidly assessed. This allows users to better understand and visualise core. This can be used to qualitatively assess non-destructive data, improve success of destructive sampling through targeted sampling and reduce the time and effort spent interacting with physical material.

Item Type:	Publication - Book Section
Digital Object Identifier (DOI):	https://doi.org/10.1144/SP527-2021-200
ISSN:	0305-8719
Date made live:	14 Nov 2022 14:17 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/533541

Item Type:

Publication - Book Section

Digital Object Identifier (DOI):

https://doi.org/10.1144/SP527-2021-200

ISSN:

0305-8719

Date made live:

14 Nov 2022 14:17 +0 (UTC)

URI:

https://nora.nerc.ac.uk/id/eprint/533541