Skip to main content

Data Science Augmented Solutions in Carbon Capture & Storage, Hydrogen Storage and CO2 EOR

Tuesday, 24 September
217 - 219
Technical Session
This technical session brings together researchers at the forefront of Carbon Capture & Storage (CCS), leveraging the power of machine learning to accelerate progress without sacrificing quality. Forecasting and optimization of CCS, Hydrogen Storage and CO2 EOR are challenging tasks due to large geological uncertainty, complex physics, and long forecast period. Data driven solutions are the key enablers of fast performance prediction and optimization under large uncertainties. This session showcases recent advances in flow simulation surrogate modeling, reduced order modeling, physics informed machine learning, and hybrid approaches of data science and physics-based modeling applied in this rapidly growing technology domain.
Session Chairpersons
Satomi Suzuki - ExxonMobil Technology & Engineering Co
Mouin Almasoodi - Devon Energy Production Co. LP
  • 1400-1425 220757
    The U-Net Enhanced Graph Convolutional Neural Network For Multiphase Flow Prediction In Complex Geological Carbon Storage
    Z. Tariq, King Abdullah University of Science and Technology; M. Abu Alsaud, Saudi Aramco PE&D; X. He, Saudi Aramco PE&D EXPEC ARC; B. Yan, S. Sun, H. Hoteit, King Abdullah University of Science & Tech
  • 1425-1450 220865
    Optimizing Hydrogen Storage In The Subsurface Using A Reservoir-simulation-based And Deep-learning-accelerated Optimization Method
    E. Eltahan, D. Albadan, K. Sepehrnoori, M. Delshad, The University of Texas At Austin; F.O. Alpak, Shell International E&P Co.
  • 1450-1515 221057
    Physics Informed Machine Learning For Reservoir Connectivity Identification And Production Forecasting In CO2-EOR
    M. Nagao, A. Datta-gupta, Texas A&M University
  • 1545-1610 220842
    Enhancing Prediction Accuracy Of Minimum Miscibility Pressure Between CO2 And Oil Phase By Integrating Improved Grey Wolf Optimization Into SVM-RF Algorithm
    Y. He, G. Zhao, Y. Tang, Southwest Petroleum University; R. Rui, University of Petroleum China Beijing; W. Yu, Texas A & M University; K. Sephernoori, The University of Texas at Austin
  • 1610-1635 220899
    Rapid Multi-objective Optimization Of Geological CO2 Sequestration In Reactive Rocks Using Coarse Grid Network Model
    B. Aslam, B. Yan, King Abdullah University of Science and Technology
  • 1635-1700 220772
    Sparsity-promoting Dynamic Mode Decomposition For Data-driven Reduced Order Modeling Of Geological Co2 Storage
    J.E. OMEKE, K. Alokla, R.E. Okoroafor, S. Misra, Texas A&M University
  • Alternate 220952
    A Machine Learning-based Co-optimization Framework For Improved Co2 Sequestration And Oil Recovery: A Gulf Of Mexico Case Study
    K. Alokla, J. OMEKE, R.E. Okoroafor, J. Lee, T. Blasingame, Texas A&M University
  • Alternate 220814
    Implementation Of A Safeguarded Deep Q-learning Network Agent For Carbon Capture Process Optimization Using Reinforcement Learning
    M. Zirrahi, C. Santiago, k. Macfarlan, SLB D&I
  • Alternate 220752
    Hybrid Approach To Determine Gas Solubility In Formation Brines For Ccs And Gas Processing Applications
    R. Ratnakar, Shell Intl E&P, Inc.; V. Chaubey, University of Michigan; S.S. Gupta, Shell Global Solutions International BV; B. Dindoruk, University of Houston

Prepare for an Unforgettable Opening Session!

Through an insightful discussion, we aim to provide a comprehensive understanding of the past, present, and future of innovation within the Oil & Gas industry, inspiring a new era of energy professionals committed to shaping a resilient and sustainable energy landscape.