Gege Wen - Stanford University - CO2 Geological Storage Modelling with Machine Learning скачать в хорошем качестве

Gege Wen - Stanford University - CO2 Geological Storage Modelling with Machine Learning

Talk given by Gege Wen from Stanford University. Recorded on October 24th 2023 CO2 geological storage plays an essential role in global decarbonization and the energy transition. Predicting the transport of CO2 in subsurface formations requires the numerical simulation of multiphase flow through porous media. However, such simulations are challenging at scale due to the high computational costs of existing numerical methods. As a result, the lack of efficient modeling approaches can lead to significant uncertainties in evaluating storage capacities and optimizing for safe and effective injection sites. This talk introduces a general-purpose machine learning-based framework that can serve as an alternative to numerical simulation for modeling CO2 geological storage. We show that the machine learning approach provides several orders of magnitude speedups compared to simulators while maintaining comparable accuracy. Our framework enables unprecedented real-time modeling to support engineering decisions and reduce uncertainties in CO2 storage deployment.