Geological Field Restoration through the Lens of Image Inpainting

TL;DR

This paper introduces a novel method for geological field reconstruction from sparse data, inspired by image inpainting, using low rank tensor modeling and optimization techniques.

Contribution

It proposes a new tensor-based inpainting approach for subsurface geological reconstruction, outperforming traditional kriging methods.

Findings

Lower relative squared error than kriging on SPE10 benchmark.

Produces visually coherent and smooth geological reconstructions.

Effective across various sampling densities.

Abstract

We study an ill-posed problem of geological field reconstruction under limited observations. Engineers often have to deal with the problem of reconstructing the subsurface geological field from sparse measurements such as exploration well data. Inspired by image inpainting, we model this partially observed spatial field as a multidimensional tensor and recover missing values by enforcing a global low rank structure together with spatial smoothness. We solve the resulting optimization via the Alternating Direction Method of Multipliers. On the SPE10 model 2 benchmark, this deterministic approach yields consistently lower relative squared error than ordinary kriging across various sampling densities and produces visually coherent reconstructions.