1887

Abstract

Summary

A data curation process of large volumes of files can be a significant undertaking when adopting a manual approach. However, the integration of various AI/ML techniques, underpinned with subsurface taxonomy and state of the art data harmonization and enrichment pipeline guided by SMEs, enables a comprehensive end-to-end curation process for classifying, extracting and transforming a large volume of data in reasonable timeframes. Also, a rigorous QC workflow is designed to evaluate the extracted data and identifying data that meet predefined quality criteria. By implementing this QC process, we ensure data suitability for subsequent analysis, thereby enhancing the reliability of the results.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539046
2025-03-24
2026-02-19
Loading full text...

Full text loading...

References

  1. AhmedT., “Reservoir Engineering Handbook” Third Edition, Gulf Professional Publishing, Oxford, UK, 2006.
    [Google Scholar]
  2. Lawrence, John J., and Deepak K.Gupta. “Quality Assessment And Consistency Evaluation Of Hydrocarbon PVT Data.” Paper presented at the International Petroleum Technology Conference, Doha, Qatar, December 2009. doi: https://doi.org/10.2523/IPTC-13784-MS
    [Google Scholar]
  3. Lun, Chin Hang, ThomasHewitt, and SongHou. “A machine learning pipeline for document extraction.” First Break40.2 (2022): 73–78.
    [Google Scholar]
  4. Paredes, J. E., Perez, R., Perera, L. M., and C. J.Larez. “Screening Criteria and Methodology for Quality Check and PVT Selection for Reservoir Studies.” Paper presented at the SPE Annual Technical Conference and Exhibition, Amsterdam, The Netherlands, October 2014. doi: https://doi.org/10.2118/170695-MS.
    [Google Scholar]
  5. Smock, Brandon, RohithPesala, and RobinAbraham. “PubTables-1M: Towards comprehensive table extraction from unstructured documents.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
    [Google Scholar]
/content/papers/10.3997/2214-4609.202539046
Loading
/content/papers/10.3997/2214-4609.202539046
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