CO2 Geological Storage Modeling with Machine Learning
Offered By: DataLearning@ICL via YouTube
Course Description
Overview
Explore a cutting-edge machine learning framework for modeling CO2 geological storage in this insightful talk by Gege Wen from Stanford University. Delve into the critical role of CO2 storage in global decarbonization efforts and the energy transition. Understand the challenges of traditional numerical simulations for predicting CO2 transport in subsurface formations, including high computational costs and scalability issues. Discover how this innovative machine learning approach offers several orders of magnitude speedup compared to conventional simulators while maintaining comparable accuracy. Learn how this framework enables real-time modeling to support engineering decisions and reduce uncertainties in CO2 storage deployment, potentially revolutionizing the evaluation of storage capacities and optimization of safe, effective injection sites.
Syllabus
Gege Wen - Stanford University - CO2 Geological Storage Modelling with Machine Learning
Taught by
DataLearning@ICL
Related Courses
L’eau et les sols - Hydrodynamique des milieux poreuxUniversité catholique de Louvain via edX Reservoir Simulation
Universidad Politécnica de Madrid via Miríadax Solutal Convection in Porous Media
Society for Industrial and Applied Mathematics via YouTube Pore to Darcy to Field Scale: Challenges in Upscaling Porous Media Models
Society for Industrial and Applied Mathematics via YouTube Opportunities for Impacting Hydrologic Model Development - Langbein Lecture
AGU via YouTube