Machine learning accelerates digital rock modeling for carbon storage

Researchers have developed a novel machine learning framework to enhance the characterization of carbonate rocks for applications like carbon storage and oil production. This framework utilizes a deep neural network (DNN) as a proxy for complex simulations, coupled with an ensemble smoother with multiple data assimilation (ESMDA) algorithm. The DNN-ESMDA approach significantly reduces computational time from thousands of hours to seconds, enabling efficient inference of rock properties and uncertainty estimation, which is crucial for high-fidelity digital rock modeling. AI

IMPACT Accelerates scientific simulation and characterization for subsurface applications like carbon storage.

RANK_REASON This is a research paper detailing a new machine learning framework for a specific scientific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• carbonate rock
• carbon storage
• X-ray computed tomography
• deep neural network
• ensemble smoother with multiple data assimilation
• Machine learning

• paper
• infra

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