SUPR
Deep Learning for Geological CT image enhancement
Dnr:

NAISS 2024/22-1140

Type:

NAISS Small Compute

Principal Investigator:

Suraj Neelakantan

Affiliation:

Örebro universitet

Start Date:

2024-09-09

End Date:

2025-09-01

Primary Classification:

10201: Computer Sciences

Allocation

Abstract

Geological CT imaging plays a vital role in various geoscience applications, such as mineral exploration, reservoir characterization, and structural geology. The challenge with these CT images lies in their often low resolution and the difficulty in distinguishing critical features such as pore structures, mineral boundaries, and fractures. Traditional super-resolution techniques have proven effective in general contexts but fall short in geological applications, where preserving domain-specific features is crucial.