Skip to main content

SPE Orange and Blue Logo ATCE
20–22 October 2025 | George R. Brown Convention Center | Houston, TX, USA

20–22 October 2025
George R. Brown Convention Center
Houston, TX, USA

SPE white Logo ATCE

20–22 October 2025
George R. Brown Convention Center
Houston, TX, USA

2025 Technical Program

Subpage Hero

SPE ATCE

Loading

Data-Driven Insights and AI Applications in Well Performance and Fracture Characterization

Wednesday, 22 October
Room 320C
Technical Session
Data-driven approaches have been developed and applied to wells and assets for more than a decade. Recent advancements strive to improve predictive capability and characterization by injecting physics. This session showcases innovative hybrid approaches that integrate physical laws, full-physics model/simulation and/or domain expertise with data analytics and artificial intelligence applied to production prediction & optimization, fracture characterization, completion optimization, wellbore flow profiling and pipe flow prediction.   
Session Chairpersons
Satomi Suzuki - ExxonMobil Technology & Engineering Co
Amr Ramadan - Khalda Petroleum Co.
  • 1400-1425 228143
    Integrating Data-driven Insights With Domain Expertise Using Agentic Conversational Analytics For Well Completions Optimization
    C. Sena Santiago, N. Shumaker, A. Weir, SLB
  • 1425-1450 227967
    Data-driven Forecasting Of Well Production Considering Re-fracturing In Shale Reservoirs
    W. Jo, Y. Lee, J. Choe, Seoul National University; S. Kim, Korea Institute of Geoscience and Mineral Resources; H. Jeong, Seoul National University
  • 1450-1515 228139
    Physics-Constrained Production Forecasting With Direct Fracture Characterization By Field Data
    Z. Xu, J. Leung, University of Alberta
  • 1515-1540 227950
    Reliable Production Optimization Using Hybrid Physics-Based Models and Data-driven Techniques
    Y. Yang, ExxonMobil Upstream Integrated Solutions Co; V. Gupta, ExxonMobil Upstream Research Co.; L. Zhang, ExxonMobil Upstream Integrated Solutions Co; B. Spivey, ExxonMobil Research & Engrg; B. Argyle, ExxonMobil Upstream Integrated Solutions Co
  • 1540-1605 228096
    Deep Learning-Driven Inversion of Natural Fractures from Fiber Optic Data in Hydraulic Fracturing
    Q. Liu, University of Texas At Austin; Y. Ou, ; M. Sharma, The University of Texas At Austin
  • 1605-1630 228112
    Data-Driven Real-Time Inversion of Hydraulic Fracture Geometry and Stress Fields Using a Deep-Kolmogorov-Arnold Network Assisted Data Assimilation Approach
    Z. Zhou, China University of Petroleum(East China); Q. Sun, Beijing Key Laboratory of Unconventional Natural Gas Geological Evaluation and Development Engineeri; B. Sun, China University of Petroleum(East China)
Search