ArXiv TLDR

Reservoir property image slices from the Groningen gas field for image translation and segmentation

🐦 Tweet
2605.03942

Abdulrahman Al-Fakih, Nabil Sariah, Ardiansyah Koeshidayatullah, SanLinn I. Kaka

cs.CVcs.DBphysics.geo-ph

TLDR

This paper introduces a new high-resolution dataset of reservoir property image slices from the Groningen gas field for ML benchmarking.

Key contributions

  • High-resolution dataset of reservoir property image slices from the Groningen gas field.
  • Contains aligned 2D PNG images for facies, porosity, permeability, and water saturation.
  • Provides a reproducible software workflow for data augmentation, mask generation, and baseline experiments.
  • Supports benchmarking of geological image analysis and cross-domain reservoir property relationships.

Why it matters

This paper addresses the critical need for open geological image datasets, enabling reproducible benchmarking for machine learning in reservoir characterization. By providing both a dataset and a workflow, it fosters transparency and accelerates research in geoscience and ML applications.

Original Abstract

Reservoir characterization workflows increasingly rely on image-based and machine-learning/deep learning or even generative AI approaches, but openly available geological image datasets suitable for reproducible benchmarking remain limited. Here we describe a high-resolution dataset of reservoir-property image slices derived from the Groningen static geological model. The dataset contains aligned two-dimensional PNG images representing facies, porosity, permeability, and water saturation, generated from three-dimensional reservoir grids and prepared for downstream visualization, segmentation, and image-to-image translation tasks. In addition to the deposited original image corpus, we provide an archived software workflow for reproducing augmentation, mask generation, paired-image construction, and example baseline experiments. The resource is designed to support benchmarking of geological image analysis methods and the study of cross-domain relationships among reservoir properties. By separating the fixed image dataset from the reproducible processing workflow, this work provides a transparent foundation for reuse in geoscience, reservoir modeling, and machine-learning applications.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.