PulseAugur
LIVE 11:07:13
research · [2 sources] ·
0
research

Geoscientists release Groningen gas field image dataset for AI analysis

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have released a new dataset of reservoir property image slices from the Groningen gas field, aimed at advancing image translation and segmentation tasks in geoscience. The dataset includes aligned 2D PNG images representing facies, porosity, permeability, and water saturation, generated from 3D reservoir grids. It is intended to support reproducible benchmarking of geological image analysis methods and facilitate the study of cross-domain relationships among reservoir properties. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Provides a benchmark dataset for applying machine learning and generative AI to geological image analysis.

RANK_REASON Academic paper release providing a new dataset for machine learning applications.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Abdulrahman Al-Fakih, Nabil Sariah, Ardiansyah Koeshidayatullah, SanLinn I. Kaka ·

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

    arXiv:2605.03942v1 Announce Type: new 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 …

  2. arXiv cs.CV TIER_1 · SanLinn I. Kaka ·

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

    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 data…

RELATED ENTITIES

RELATED TOPICS