Technical Session 1: Gen AI
Generative Artificial Intelligence (GenAI) is transforming industries across multiple dimensions—driving innovation, enhancing performance, and fostering responsible stewardship of resources. In addition to empowering sustainable practices and reduced carbon footprints, GenAI offers opportunities for businesses to streamline processes, improve productivity, and ensure workplace safety.
Organisations are leveraging GenAI to pioneer breakthroughs in areas such as predictive reservoir characterisation, automated seismic interpretation, and optimal drilling trajectory design—resulting in significant reductions in exploration costs, increased hydrocarbon recovery rates, and enhanced asset lifespan. Moreover, GenAI is enabling the fusion of diverse geospatial datasets, streamlined geological modeling, and robust uncertainty quantification, ultimately leading to safer, more efficient, and environmentally conscious extraction operations.
Though, despite its vast potential, adoption of GenAI poses notable technical and practical challenges such as scarcity of labeled data, computational intensity, and difficulties in interpreting results. Furthermore, translating insights into actionable recommendations, and upholding stringent standards for transparency, accountability, and human oversight.
This symposium invites pioneers at the intersection of AI research, business strategy, and industry expertise to share novel ideas, models, tools, and experiences aimed at tackling these obstacles accelerating the application of GenAI through sustainable practice transformations, advanced data-driven optimisation methodologies, energy efficiency enhancements, and comprehensive prediction frameworks.
Primary | 11:00 – 11:30 |
Accelerating Seismic Processing with GenAI-Powered FFT by Leveraging Deep Learning Technologies |
Primary | 11:30 – 12:00 |
A deep learning model for leakage identification in multiphase flow systems |
Primary | 12:00 – 12:30 | Large World Model for Robust Molten Salt Nuclear Simulation Muhammad Hakami, Elm |
Alternate / ePoster | TBC | Mixture-of-Experts AI Framework for Enhanced Oil & Gas Field Analysis Zhenlin Chen, Stanford University |
Alternate / ePoster | TBC | AI & GenAI-Driven Optimized CapEx Forecasting for Onshore Oil Development Wells Shahad Alansari, Aramco |
Alternate / ePoster | TBC | An Evolving GenAI Assistant for Intelligent Generation of Well-Integrity Reports Ayman El Aassal, GOWell |
Alternate / ePoster | TBC | Generative Diffusive Learning for Simulation Model History Matching (SimGDL): Generalization and Scale-up Marko Maucec, Aramco |