# Geological Field Restoration through the Lens of Image Inpainting

arXiv: https://arxiv.org/abs/2506.04869 · HTML: https://mlsanity.com/paper/2506.04869/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 4 of 4)

- [Image inpainting: A review](https://mlsanity.com/paper/1909.06399/) (2019)
- [A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation](https://mlsanity.com/paper/2003.10271/) (2020)
- [Tensor Completion by Alternating Minimization under the Tensor Train (TT) Model](https://mlsanity.com/paper/1609.05587/) (2016)
- [Bayesian Methods in Tensor Analysis](https://mlsanity.com/paper/2302.05978/) (2023)

## Abstract (arXiv)

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.