Skip to main content
Loading

Digital Transformation and AI: Innovative Machine Learning Applications in the Energy Sector and Reservoir Management

Wednesday, 11 June
Hall D2
Technical Session
This session explores the integration of AI and machine learning in energy sector applications. Topics include self-supervised learning for rock image segmentation, production time-series monitoring with vision-language models, and data-driven reservoir performance forecasting. We'll also discuss predicting liquid loading using hybrid models, synthetic data-enhanced retrieval for energy-specific tasks, time-to-event analysis for shale reservoir performance, and AI-based anomaly detection in surface logging data. Join us to discover these cutting-edge advancements in AI and machine learning for energy.
Session Chairpersons
Pejman Shoeibi Omrani - TNO
I. Yucel Akkutlu - Texas A&M University (PE DEPT)
  • 1525-1550 225609
    Self-supervised Learning Using Vision Transformer Architecture For Rock Image Segmentation
    D. Devegowda, University of Oklahoma
  • 1550-1615 225545
    Production Time-series Monitoring Using Vision-language Models
    H. Nese, K.J. Mann, S. Sæten, L.J. Mosser, AkerBP
  • 1615-1640 225507
    Data-driven Reservoir Performance Forecasting: Leveraging Machine Learning For Complex Reservoirs
    S. Canbolat, Turkish Petroleum Off-Shore Technology Center; M. Cicek, Turkish Petroleum Offshore Technology Center; E. Artun, Sultan Qaboos University
  • 1640-1705 225515
    Prediction Of Liquid Loading Using Physics-based And Data Driven Machine Learning Model For A German Gas Field
    M. Eita, Baker Hughes
  • Alternate 225535
    Time-to-event Analysis Of Shale Reservoir Performance For Identification Of Key Performance Drivers
    E. Artun, Sultan Qaboos University; A. AL Amri, Petroleum Development Oman
  • Alternate 225579
    Detecting Low-quality Intervals In Surface Logging Data Using AI-based Anomaly Detection
    F. Concina, A. Nadirkhanlou, Kwantis