ML framework enhances gas flow modeling in porous media

Researchers have developed a novel machine learning framework to improve the modeling of gas flow in porous media. This approach combines a Klinkenberg-enhanced constitutive relation with a Hopf-Cole transformation to linearize the governing equations. A shared-trunk neural network architecture and a Deep Least-Squares solver are used for accurate prediction of pressure and velocity fields, also enabling inverse modeling for parameter estimation. AI

IMPACT This framework offers a more accurate and computationally efficient method for simulating gas transport and estimating flow properties in challenging geological formations.

RANK_REASON The cluster contains a research paper detailing a new methodology for modeling gas flow in porous media. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Darcy
• Kalyana Babu Nakshatrala
• Klinkenberg

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →