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 to well operations: Drilling and geoscience applications

Wednesday, 22 October
Room 332AD
Technical Session
From use-cases on real-time drilling dysfunction, hydraulic fracturing designs, predictive maintenance, causal inference methodologies, extracting insights from drilling data with LLMs, analysis of wave-induced heave effects on drilling dynamics, to compositional fluid analysis, our technical session will show a diverse set of insights on data-driven solutions for well operations. Examples of how data science and machine learning applied to both well drilling and geoscience workflows with diverse methodologies can effectively give insights to wells, geoscience and operational decision making.
Session Chairpersons
Michael Edwards - Partners in Performance
Timothy Robinson - Exebenus
  • 0830-0855 227965
    Real-Time Bit Performance Monitoring: A Dual-Dimensional Graph Attention Network with Multivariate Time-Series Data
    R. Zhang, College of Artificial Intelligence, China University of Petroleum; X. Song, S. Ye, Z. Zhu, China University of Petroleum; Research Center for Intelligent Drilling & Completion Technology and ; Y. Wu, B. Li, CNOOC Research Institute Co., Ltd; H. Liu, China University of Petroleum; B. Bijeljic, M. Blunt, Department of Earth Science and Engineering, Imperial College London
  • 0855-0920 228194
    Stop Using Convolutional Neural Networks: Knowledge Distillation for An Interpretable and Lightweight Decision Tree in Rod Pump Working Condition Diagnosis
    Q. Mao, University of British Columbia; X. Yang, University of Calgary; J. Yang, PetroChina Changqing Oilfield Company; Y. Cao, University of British Columbia
  • 0920-0945 228015
    Machine Learning Approaches for Compositional Fluid Analysis in Logging While Drilling Using Near-infrared Data
    W. Weinzierl, P. Schapotschnikow, Baker Hughes; J. Denninger, RWTH Aachen; E. Niemeyer, Baker Hughes; A. Adams, RWTH Aachen; A. Cartellieri, Baker Hughes
  • 1015-1040 227859
    Beyond Static Near-Wellbore Data: Optimization of Hydraulic Fracturing Parameters Under Co-Evolution Constraints of Fracture Networks and Geological Spatial Fields
    Z. Ma, J. Zhang, T. Wang, G. Li, S. Tian, State Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)
  • 1040-1105 228051
    A Causal Inference Pipeline for Injection Open-Source Methodology and Implementation
    L. Matthews, Project Geminae; A. Molak, Causal Python; C. Reudelhuber, Self; T. Meek, E. Rensi, Project Geminae; I. Ayala Portella, Gradient Insight
  • 1105-1130 228186
    An Integrated Geology and Engineering Workflow for Optimal Hydraulic Fracturing Design in Deep Coalbed Methane Multiwells Pads
    R. Yang, W. Shi, China University of Petroleum Beijing; Y. Li, CNOOC EnerTech-Drilling & Production Co.; Y. Gong, Z. Huang, G. Li, China University of Petroleum Beijing
  • Alternate 228061
    Exploring Modern Feature Extraction Techniques for Improved Offshore Fault Detection in Oil and Gas Operations
    R. Wibawa, M. Wang, B. Jha, University of Southern California
Search