1887

Abstract

Summary

This work presents a novel, end-to-end machine learning workflow for geological image analysis, addressing the time-consuming and subjective nature of traditional methods. While the use of ResNet Convolutional Neural Networks (CNNs) for core image interpretation is not new, our core innovation lies in creating a flexible and integrated workflow.

Our in-house system automates the extraction of key rock properties like lithofacies, porosity, and permeability. Crucially, this system is integrated into a custom-built plugin within a commercial solution, allowing geological experts to review, fine-tune, and correct AI-generated results for production. This human-in-the-loop approach not only ensures high-quality output but also facilitates a virtuous cycle of continuous improvement by feeding validated data back into the machine learning models, laying the foundation for fully automated MLOps. This integrated system is projected to save over $100,000 annually in rock image analysis, significantly enhancing efficiency and accuracy in geological interpretation.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202577070
2025-11-18
2026-01-20

  • From This Site

    /content/papers/10.3997/2214-4609.202577070
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Bouziat, A., Desroziers, S., Feraille, M., Lecomte, J., Divies, R., and Cokelaer, F. [2020]. Deep Learning Applications to Unstructured Geological Data: From Rock Images Characterization to Scientific Literature Mining. First EAGE Digitalization Conference and Exhibition, 1–5. https://doi.org/10.3997/2214-4609.202032047
     [Google Scholar]
  2. Deng, J., Dong, W., Socher, R., Li, L.-J., KaiLi, and LiFei-Fei. [2009]. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Presented at the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), Miami, FL. https://doi.org/10.1109/cvpr.2009.5206848
     [Google Scholar]
  3. Ekkawong, P., Kritsadativud, P., and Lerlertpakdee, P. [2015]. Automated Optimization of Interdependent Artificial Lifting Fields Using Integrated Response Surface Model and Hybrid Heuristic-Gradient Algorithm: A Field Case Study. SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition. Presented at the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Nusa Dua, Bali, Indonesia. https://doi.org/10.2118/176416-ms
     [Google Scholar]
  4. Ekkawong, P., Loboonlert, P., Seusutthiya, K., Wongpattananukul, K., Laoniyomthai, N., Thapchim, J., … Lhosupasirirat, K. [2021]. Algorithm-Assisted Platform Location Optmisation Using Mixed-Integer Programming for Cluster Development Strategy in the Gulf of Thailand. SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition. Presented at the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Virtual. https://doi.org/10.2118/205765-ms
     [Google Scholar]
  5. He, K., Zhang, X., Ren, S., and Sun, J. [2015, December 10]. Deep Residual Learning for Image Recognition. https://doi.org/10.48550/arXiv.1512.03385
     [Google Scholar]
  6. Lechevallier, A., Bouziat, A., and Desroziers, S. [2021]. Assisted interpretation of core images with Deep Learning workflows: lessons learnt from a practical use case. Second EAGE Workshop on Machine Learning, 1–3. https://doi.org/10.3997/2214-4609.202132003
     [Google Scholar]
  7. Palviriyachote, S., Misra, S., Moelyono, S., Ekkawong, P., and Tonburinthip, T. [2024]. Unlocking the Potential of Mud Logs and LWD in the Gulf of Thailand Using Machine Learning. ADIPEC. Presented at the ADIPEC, Abu Dhabi, UAE. https://doi.org/10.2118/222299-ms
     [Google Scholar]
  8. Tonburinthip, T., and Norasaed, W. [2024]. Revolutionizing the Perforation Process Via an End-To-End Automated Perforation Toolbox in the Gulf of Thailand (PerfSight). ADIPEC. Presented at the ADIPEC, Abu Dhabi, UAE. https://doi.org/10.2118/222615-ms
     [Google Scholar]
/content/papers/10.3997/2214-4609.202577070
Loading
Augmented Geologic Interpretation: Integrated End-To-End AI-Powered Core Image Description Analysis
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202577070
/content/papers/10.3997/2214-4609.202577070
/content/papers/10.3997/2214-4609.202577070
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

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