1887

Abstract

Summary

Over the past 45 years, data collection from oil and gas operations have cost billions of pounds to acquire and digitize. While UK legislations aim to make this data is publicly available, it is often not accessible in a consistent format that is fit for purpose. To help solve this issue, The Sand Injectite Research Group at the University of Aberdeen developed an extensive, relational core database that integrates raw and interpreted data for over 3,000 cored wells, predominantly from the UKCS. The database incorporates over 800,000 core analysis plugs broken down to a stratigraphic level along with core images, log data and supporting datasets, providing an essential tool for geological research. To further unlock the full potential of legacy data, the database is used for ML applications to predict lithofacies from core images to minimize manual interpretation. This combined approach supports the ongoing efforts to standardize subsurface data and to ensure accessibility and utility for academic and industrial application.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539095
2025-03-24
2026-02-14
Loading full text...

Full text loading...

References

  1. Di Martino, A., Carlini, G., Castellani, G., Remondini, D., & Amorosi, A. (2023). Sediment core analysis using artificial intelligence.
    [Google Scholar]
  2. Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation.
    [Google Scholar]
  3. The Open Group. (2024). Rock and Fluid Sample Analysis - OSDU Data Definitions. GitHub Repository.
    [Google Scholar]
/content/papers/10.3997/2214-4609.202539095
Loading
/content/papers/10.3997/2214-4609.202539095
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error