Lead Organizer: Shuyu Sun - King Abdullah University of Science and Technology, Saudi Arabia
- Bailian Chen - Los Alamos National Laboratory, USA
- Huangxin Chen - Xiamen University, China
- Yalchin Efendiev - Texas A&M University, USA
- Ahmed H. Elsheikh - Heriot-Watt University, UK
- Cunqi Jia - The University of Texas at Austin, USA
- He Liu - China National Petroleum Corporation, China
- Xueying Lu - The University of Texas at Austin, USA
- Kai Zhang - Qingdao University of Technology, China
- Tao Zhang - China University of Petroleum (East China), China
Recent advances in computer and data sciences have made machine learning (ML) techniques a frontier in porous media-related research. As a result, classical challenges in porous media are being addressed with new techniques based on ML. The aim of this mini-symposium is to present the recent results of new ML methods and introduce new directions in porous media-related research to researchers in our community. This session seeks abstracts in the following topics: 1) recent advances in ML algorithms (including deep learning architectures, physics-informed ML, self-supervised/un-supervised ML, transferability, interpretability) with applications to porous media; 2) development of computationally fast proxy models, reduced order models or predictive empirical models using ML to address issues of interest in porous media; 3) other ML-/big data-related applications or developments (e.g., upscaling, multiscale analysis, porous media generation, imaging analysis, coupled processes) in porous media.
