Skip to main content
Loading

Advanced Machine Learning Techniques for Production Optimization

Wednesday, 25 September
Room 231 - 232
Technical Session
This session brings together innovative approaches and cutting-edge research aimed at optimizing production in the producing assets. From leveraging machine learning and artificial intelligence to integrating expert systems and hybrid models, the papers presented in this session showcase a diverse range of methodologies and technologies. Attendees will gain insights into production prediction, gas flow rate estimation, anomaly detection, survival analysis, and the quantification of geological and completion parameters' effects on well performance. Additionally, the advancements in production optimization through hybrid data-physics architectures and comparative analyses of completion and reservoir data will be discussed. Furthermore, the session will explore novel frameworks for engineering data augmentation, and graph-level feature embedding methods for interconnected well production forecasting. Join us to discover the latest advancements shaping the future of production optimization.
Session Chairpersons
Bo Hu - ConocoPhillips Co
Hossein Nourozieh - Parex Resources
  • 0830-0855 220903
    Gas Flow Rate Estimation With Artificial Intelligence: Bridging Reality Through Computer Vision And Machine Learning
    V. Santhalingam, A. Abinader, V. Vesselinov, D. Krishna, Schlumberger
  • 0855-0920 220826
    Gas Lift Anomaly Detection In Unconventional Fields Using Expert System Techniques
    A. Zejli, A. Shrestha, B. Cormier, Chevron
  • 0920-0945 220995
    A Hybrid Tabular-Spatial-Temporal Model with 3D Geo-model for Production Prediction in Shale Gas Formations
    M. Wang, H. Wang, S. Chen, G. Hui, Z. Xue, University of Calgary
  • 1015-1040 221041
    ESP Wells Dynamic Survival Analysis And Lifespan Prediction Using Machine Learning Algorithms
    G. Han, X. Lu, China University of Petroleum-Beijing; H. Zhang, University of Houston-Victoria; X. Sui, B. Wang, National Key Laboratory of Offshore Oil and Gas Exploitation; K. Ling, University of North Dakota
  • 1040-1105 220966
    Two-Step Process to Quantify Effects of Geological and Completion Parameters on Unconventional Wells Performance
    M. Kelkar, University of Tulsa; A. Itteyra, Kelkar and Associates, Inc.
  • 1105-1130 220790
    Graph-Level Feature Embedding with Spatial-Temporal GCN Method for Interconnected Well Production Forecasting
    Z. Xu, J. Leung, University of Alberta
  • Alternate 220777
    Advancements In Production Optimization Through An Innovative Hybrid Data-Physics Architecture
    R. Matoorian, University of Calgary; M. Malaieri, Computer Modelling Group Ltd.; R. Shor, Texas A&M University; R. Aguilera, University of Calgary
  • Alternate 220937
    A Comparative Analysis Of Completion And Reservoir Data To Decipher Productivity Drivers In North American Tight And Shale Plays
    V. Indina, H. Singh, Y. Liu, Y. Gu, CNPC USA; H. Song, China Petroleum Enterprise Association; C. Li, D. Zhang, F. Kong, P. Cheng, Z. Li, W. Li, CNPC USA
  • Alternate 220954
    ConGANergy: A Framework for Engineering Data Augmentation with Application to Solid Particle Erosion
    J. Zhang, Y. Li, W. Pei, The University of Tulsa; S. Shirazi, University of Tulsa