pith. machine review for the scientific record. sign in

arxiv: 2605.03942 · v1 · submitted 2026-05-05 · 💻 cs.CV · physics.geo-ph

Recognition: unknown

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

Abdulrahman Al-Fakih , Nabil Sariah , Ardiansyah Koeshidayatullah , SanLinn I. Kaka
Authors on Pith no claims yet

Pith reviewed 2026-05-07 03:49 UTC · model grok-4.3

classification 💻 cs.CV physics.geo-ph
keywords reservoir characterizationgeological image datasetimage segmentationimage-to-image translationGroningen gas fieldfacies modelingporosity permeabilitymachine learning in geoscience
0
0 comments X

The pith

A dataset of aligned 2D PNG images showing facies, porosity, permeability and water saturation from the Groningen gas field model is released with its full reproduction workflow.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper creates and describes a collection of two-dimensional image slices extracted from a three-dimensional static geological model of the Groningen gas field. Each slice set contains matched PNG images that represent different reservoir properties on the exact same spatial grid. The authors also deposit the software that generates augmentations, property masks, paired training examples, and sample baseline runs for segmentation and translation tasks. This resource exists because openly available, high-resolution geological image collections suitable for machine-learning benchmarking have been scarce. A reader would care because the fixed images and the separate, archived workflow together let others run reproducible experiments on real reservoir data without having to rebuild the underlying 3D model.

Core claim

The authors supply a corpus of aligned two-dimensional PNG images that depict facies, porosity, permeability, and water saturation, all derived from the same three-dimensional reservoir grids of the Groningen static geological model, together with an archived software workflow that can reproduce augmentation steps, mask generation, paired-image construction, and example baseline experiments for downstream visualization, segmentation, and image-to-image translation tasks.

What carries the argument

The set of aligned 2D PNG image slices, one per reservoir property, generated directly from 3D grid cells so that corresponding pixels across properties occupy identical spatial locations.

If this is right

  • Researchers can train and compare segmentation models directly on the released facies, porosity, permeability, and saturation images without generating new data.
  • Paired images enable image-to-image translation experiments that map one reservoir property onto another while preserving exact spatial registration.
  • The deposited workflow allows any user to regenerate augmented training sets or custom masks under identical conditions for fair benchmarking.
  • Cross-property studies become possible because every slice set shares the same grid coordinates, letting models learn relationships among facies, porosity, permeability, and saturation.
  • The separation of the fixed image corpus from the reproduction code creates a transparent baseline that other groups can extend to additional geological models.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same alignment could support multi-task learning models that predict several reservoir properties from a single input image.
  • Because the workflow is archived separately, groups could adapt it to slice other public or proprietary 3D models and thereby enlarge the collection of comparable datasets.
  • The images may serve as a testbed for generative models that synthesize new realizations of reservoir properties while respecting the observed spatial statistics.
  • If property patterns learned on these Groningen slices transfer to other fields, the dataset could reduce the need for site-specific data collection in early reservoir modeling stages.

Load-bearing premise

Slicing the original three-dimensional geological model into two-dimensional images preserves the essential spatial relationships and property distributions without introducing significant artifacts or information loss.

What would settle it

Running the archived workflow on the provided three-dimensional grids and obtaining image files that differ in pixel values or alignment from the deposited PNG corpus would show the release does not faithfully reproduce its own source data.

read the 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper describes and releases a high-resolution dataset of aligned two-dimensional PNG images representing facies, porosity, permeability, and water saturation, derived from the three-dimensional static geological model of the Groningen gas field. It also provides an archived software workflow for reproducing augmentation, mask generation, paired-image construction, and example baseline experiments to support visualization, segmentation, and image-to-image translation tasks in reservoir characterization and machine learning.

Significance. If the 2D image slices accurately capture the essential spatial relationships and property distributions from the 3D model, this resource would significantly contribute to the field by filling the gap in openly available geological image datasets for reproducible benchmarking. The inclusion of both the fixed image corpus and the reproducible processing workflow strengthens its value for geoscience, reservoir modeling, and ML applications, allowing transparent reuse and extension. The authors are to be credited for making the dataset and tools publicly available to facilitate such research.

major comments (1)
  1. [Dataset Generation] The claim that the PNG images are suitable for segmentation and image-to-image translation (Abstract) depends on the 2D slices faithfully preserving 3D property distributions and alignments. However, the manuscript provides no quantitative validation such as histogram comparisons, variogram analysis, or preservation metrics for spatial continuity and cross-property correlations. Furthermore, there is no discussion of how continuous properties are quantized into 8-bit PNG values or how the grid-to-pixel mapping accounts for partial cells, raising the risk that the dataset contains artifacts rather than true geological features.
minor comments (2)
  1. The manuscript could benefit from a table summarizing the dataset statistics, such as number of images, resolutions, and value ranges for each property.
  2. [Workflow Description] Provide more explicit details on the file structure of the deposited dataset and how to use the software for generating paired images.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive review and the positive evaluation of the dataset's significance for geoscience and ML applications. We address the single major comment point by point below. The revisions we outline will be incorporated in the next version of the manuscript.

read point-by-point responses

  1. Referee: [Dataset Generation] The claim that the PNG images are suitable for segmentation and image-to-image translation (Abstract) depends on the 2D slices faithfully preserving 3D property distributions and alignments. However, the manuscript provides no quantitative validation such as histogram comparisons, variogram analysis, or preservation metrics for spatial continuity and cross-property correlations. Furthermore, there is no discussion of how continuous properties are quantized into 8-bit PNG values or how the grid-to-pixel mapping accounts for partial cells, raising the risk that the dataset contains artifacts rather than true geological features.

    Authors: We agree that the original manuscript would be strengthened by an explicit description of the slicing and quantization procedures together with basic quantitative checks on property preservation. The 2D PNG slices are obtained by extracting entire horizontal layers from the structured 3D grid at regular depth intervals; each pixel therefore corresponds exactly to one grid cell and inherits its property value directly from the model. Continuous properties (porosity, permeability, water saturation) are mapped to 8-bit integers via linear min-max scaling using the global extrema of each property over the full 3D volume. Because the slices coincide with grid planes, no partial-cell interpolation occurs. We acknowledge that the submitted text did not contain histogram comparisons, variogram analysis, or a dedicated discussion of these steps. In the revised manuscript we have expanded the Dataset Generation section to document the slicing, scaling, and mapping procedures in full. We have also added supplementary figures that compare property histograms between the original 3D model and the extracted 2D slices, together with a short discussion of spatial continuity. These additions directly address the concern about potential artifacts and provide the quantitative support needed to justify the dataset's suitability for segmentation and image-to-image translation tasks. revision: yes

Circularity Check

0 steps flagged

No circularity: dataset release paper with no derivations, predictions, or equations

full rationale

The manuscript is a data-release paper that describes the generation of 2D PNG image slices (facies, porosity, permeability, water saturation) from an existing 3D Groningen static geological model, along with accompanying software for augmentation and paired-image construction. No equations, first-principles derivations, fitted parameters, or predictive claims appear in the abstract or described content. The central statements are factual descriptions of a processing pipeline (slicing 3D grids into aligned 2D images) rather than results that reduce to their own inputs by construction. No self-citations are load-bearing for any derivation, and no uniqueness theorems or ansatzes are invoked. The paper is therefore self-contained as a transparent data and tool release; the absence of any derivation chain precludes circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

This is a data-release paper with no mathematical derivations or fitted parameters. The central contribution rests on the domain assumption that the source 3D static geological model is a reliable representation of the reservoir and that the slicing and property extraction process introduces no critical artifacts.

axioms (1)
  • domain assumption The static geological model of the Groningen field accurately represents the reservoir properties.
    The 2D images are generated directly from this model, so its fidelity is required for the dataset to be representative of real reservoir conditions.

pith-pipeline@v0.9.0 · 5471 in / 1506 out tokens · 63193 ms · 2026-05-07T03:49:21.053720+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

42 extracted references · 36 canonical work pages

  1. [1]

    Al-Fakih, A. A. Original Datasets. Zenodo https://doi.org/10.5281/zenodo.14603410 (2025)

    work page doi:10.5281/zenodo.14603410 2025

  2. [2]

    Al-Fakih, A. A. ARhaman/GeoPix: Geop. Zenodo https://doi.org/10.5281/zenodo.14639446 (2025)

    work page doi:10.5281/zenodo.14639446 2025

  3. [3]

    Jafarizadeh, B., & Bratvold, R. B. (2009, April). Strategic decision making in the digital oil field. Paper presented at the SPE Digital Energy Conference and Exhibition, Houston, Texas, USA. https://doi.org/10.2118/123213-MS

    work page doi:10.2118/123213-ms 2009

  4. [4]

    Uliasz-Misiak, B., Lewandowska-Śmierzchalska, J., & Matuła, R. (2021). Criteria for selecting sites for integrated CO₂ storage and geothermal energy recovery. Journal of Cleaner Production, 285, 124822. https://doi.org/10.1016/j.jclepro.2020.124822

    work page doi:10.1016/j.jclepro.2020.124822 2021

  5. [5]

    Seyyedattar, M., Zendehboudi, S., & Butt, S. (2020). Technical and non-technical challenges of development of offshore petroleum reservoirs: Characterization and production. Natural Resources Research, 29, 2147–2189. https://doi.org/10.1007/s11053-019-09549-7

    work page doi:10.1007/s11053-019-09549-7 2020

  6. [6]

    D., Davis, J

    Callas, C., Saltzer, S. D., Davis, J. S., Hashemi, S. S., Kovscek, A. R., Okoroafor, E. R., Wen, G., Zoback, M. D., & Benson, S. M. (2022). Criteria and workflow for selecting depleted hydrocarbon reservoirs for carbon storage. Applied Energy, 324, 119668. https://doi.org/10.1016/j.apenergy.2022.119668

    work page doi:10.1016/j.apenergy.2022.119668 2022

  7. [7]

    Pyrcz, M.J., Janele, P., Weaver, D., Strebelle, S. (2017). Geostatistical Methods for Unconventional Reservoir Uncertainty Assessments. In: Gómez-Hernández, J., Rodrigo- Ilarri, J., Rodrigo-Clavero, M., Cassiraga, E., Vargas-Guzmán, J. (eds) Geostatistics Valencia

    2017

  8. [8]

    Springer, Cham

    Quantitative Geology and Geostatistics, vol 19. Springer, Cham. https://doi.org/10.1007/978-3-319-46819-8_45

    work page doi:10.1007/978-3-319-46819-8_45

  9. [9]

    Cannon, S. (2024). Reservoir Modelling: A Practical Guide. John Wiley & Sons

    2024

  10. [10]

    Chen, M., Wu, S., Bedle, H., Xie, P., Zhang, J., & Wang, Y. (2021). Bridging paired and unpaired medical image translation. Medical Image Analysis, 34, 123–140. https://doi.org/10.1016/j.media.2021.101813

    work page doi:10.1016/j.media.2021.101813 2021

  11. [11]

    B., Ochulor, O

    Solanke, B., Onita, F. B., Ochulor, O. J., & Iriogbe, H. O. (2024). Techniques for improved reservoir characterization using advanced geological modeling in the oil and gas industry. International Journal of Applied Research in Social Sciences. https://doi.org/10.51594/ijarss.v6i9.1542

    work page doi:10.51594/ijarss.v6i9.1542 2024

  12. [12]

    E., Jones, S

    Obradors-Prats, J., Calderon Medina, E. E., Jones, S. J., Rouainia, M., Aplin, A. C., & Crook, A. J. L. (2023). Integrating petrophysical, geological and geomechanical modelling to assess stress states, overpressure development and compartmentalisation adjacent to a salt wall, Gulf of Mexico. Marine and Petroleum Geology, 155, 106352. https://doi.org/10.1...

    work page doi:10.1016/j.marpetgeo.2023.106352 2023

  13. [13]

    S., & Dimri, V

    Ganguli, S. S., & Dimri, V. P. (2023). Chapter One – Reservoir characterization: State-of- the-art, key challenges and ways forward. In S. S. Ganguli & V. P. Dimri (Eds.), Developments in Structural Geology and Tectonics (Vol. 6, pp. 1–35). Elsevier. https://doi.org/10.1016/B978-0-323-99593-1.00015-X

    work page doi:10.1016/b978-0-323-99593-1.00015-x 2023

  14. [14]

    J., Bollt, E., Griffith, A., & Barbosa, W

    Gauthier, D. J., Bollt, E., Griffith, A., & Barbosa, W. A. (2021). Next generation reservoir computing. Nature Communications, 12(1), 1–8. https://doi.org/10.1038/s41467-021-25801- 2

    work page doi:10.1038/s41467-021-25801- 2021

  15. [15]

    Goodfellow, I. et al. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems, 27, 2672–2680

    2014

  16. [16]

    Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1125–1134). https://doi.org/10.1109/CVPR.2017.632

    work page doi:10.1109/cvpr.2017.632 2017

  17. [17]

    Pan, W., Torres-Verdín, C., & Pyrcz, M. J. (2021). Stochastic pix2pix: A new machine learning method for geophysical and well conditioning of rule-based channel reservoir models. Natural Resources Research, 30, 1319–1345. https://doi.org/10.1016/j.nrr.2021.03.005

    work page doi:10.1016/j.nrr.2021.03.005 2021

  18. [18]

    Song, Y., Wu, J., Xu, Z., & Wang, Y. (2022). A data-driven approach to rock facies classification using conditional GANs. Journal of Petroleum Science and Engineering, 208, 109351. https://doi.org/10.1016/j.petrol.2021.109351

    work page doi:10.1016/j.petrol.2021.109351 2022

  19. [19]

    A., Mukerji, T., Kanfar, R., Alali, A., & Kaka, S

    Al-Fakih, A., Koeshidayatullah, A., Saraih, N. A., Mukerji, T., Kanfar, R., Alali, A., & Kaka, S. I. (2026). Pix2Geomodel: A next-generation reservoir geomodeling with property-to- property translation. Geoenergy Science and Engineering, 258, 214342. https://doi.org/10.1016/j.geoen.2025.214342

    work page doi:10.1016/j.geoen.2025.214342 2026

  20. [20]

    Koeshidayatullah, N

    Al-Fakih, A. Koeshidayatullah, N. Saraih and S. Kaka1, Bridging Reservoir‑ and Pore‑Scale Modeling with Pix2Pix cGANs, Second EAGE Workshop on Advances in Carbonate Reservoirs: from Prospects to Development, Kuwait, Apr 2026, Volume 2026, p.1 – 3. https://doi.org/10.3997/2214-4609.2026649005

    work page doi:10.3997/2214-4609.2026649005 2026

  21. [21]

    Koeshidayatullah, N

    Saraih, Al-Fakih, A. Koeshidayatullah, N. Saraih and S. Kaka1 Improving Facies and Property Prediction in Complex Reservoirs Using Enhanced Pix2Pix-Based Modeling, Second EAGE Workshop on Advances in Carbonate Reservoirs: from Prospects to Development, Kuwait, Apr 2026, Volume 2026, p.1 – 3. https://doi.org/10.3997/2214- 4609.2026649024

    work page doi:10.3997/2214- 2026

  22. [22]

    Al-Fakih,A., Hanafy, S., Saraih, N., Koeshidayatullah, A., and Kaka, S.: Data-efficient enhanced Pix2Geomodel.v2 for complex facies settings, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-2220, https://doi.org/10.5194/egusphere-egu26- 2220, 2026

    work page doi:10.5194/egusphere-egu26- 2026

  23. [23]

    Kaka, S., Al-Fakih, A., Saraih, N., Koeshidayatullah, A., and Hanafy, S.: Bidirectional translation + spatial continuity validation, EGU General Assembly 2026, Vienna, Austria, 3– 8 May 2026, EGU26-2222, https://doi.org/10.5194/egusphere-egu26-2222, 2026

    work page doi:10.5194/egusphere-egu26-2222 2026

  24. [24]

    (2023, May 2)

    Matenco, L., & Beekman, F. (2023, May 2). Integrating the geological database of the subsurface of the Netherlands, for efficient visualization and interpretation (Version 3.4). Utrecht University, EPOS-NL. https://doi.org/10.24416/UU01-7M15N6

    work page doi:10.24416/uu01-7m15n6 2023

  25. [25]

    Petrel Geological Model of the Groningen Gas Field, the Netherlands

    NAM (2020). Petrel Geological Model of the Groningen Gas Field, the Netherlands. Open access through EPOS-NL. Yoda Data Publication Platform, Utrecht University. https://doi.org/10.24416/UU01-1QH0MW

    work page doi:10.24416/uu01-1qh0mw 2020

  26. [26]

    Zhang, B., Tong, Y., Du, J., Hussain, S., Jiang, Z., Ali, S., Ali, I., Khan, M., & Khan, U. (2022). Three-Dimensional Structural Modeling (3D SM) and Joint Geophysical Characterization (JGC) of Hydrocarbon Reservoir. Minerals, 12(3), 363. https://doi.org/10.3390/min12030363

    work page doi:10.3390/min12030363 2022

  27. [27]

    A., & Solano Viota, J

    Visser, C. A., & Solano Viota, J. L. (2017). Introduction to the Groningen static reservoir model. Netherlands Journal of Geosciences, 96(S5), s39–s46. https://doi.org/10.1017/njg.2017.25

    work page doi:10.1017/njg.2017.25 2017

  28. [28]

    de Jager , J., & Visser , C. (2018). Geology of the Groningen field – an overview. Netherlands Journal of Geosciences, 96, 3–15. https://doi.org/10.1017/njg.2017.22

    work page doi:10.1017/njg.2017.22 2018

  29. [29]

    Glennie, K. (2000). Exploration activities in the Netherlands and North-West Europe since Groningen. Netherlands Journal of Geosciences, 80(1), 33-52. https://doi.org/10.1017/S0016774600022150

    work page doi:10.1017/s0016774600022150 2000

  30. [30]

    Grötsch, J., & Gaupp, R. (Eds.). (2011). The Permian Rotliegend of the Netherlands (Vol. 98, pp. 11-33). Tulsa: SEPM (Society for Sedimentary Geology)

    2011

  31. [31]

    50 Years of Groningen Gas

    Dijksman, Niels, and Joris Steenbrink. Managing a Giant" 50 Years of Groningen Gas." Paper presented at the SPE Offshore Europe Oil and Gas Conference and Exhibition, Aberdeen, UK, September 2009. doi: https://doi.org/10.2118/123931-MS

    work page doi:10.2118/123931-ms 2009

  32. [32]

    M., Underhill, J

    Wijanarko, R. M., Underhill, J. R., Brackenridge, R. E., & Fyfe, L.-J. (2025). Basin transection in the Vale of Pickering, North Yorkshire: Implications for energy resources and geological storage. Energy Geoscience Conference Series, 1(1). https://doi.org/10.1144/egc1- 2024-16

    work page doi:10.1144/egc1- 2025

  33. [33]

    M., Girard, J., Schöner, R., & Gaupp, R

    Miocic, J. M., Girard, J., Schöner, R., & Gaupp, R. (2020). Mudstone/sandstone ratio control on carbonate cementation and reservoir quality in Upper Permian Rotliegend sandstones, offshore the Netherlands. Marine and Petroleum Geology, 115, 104293. https://doi.org/10.1016/j.marpetgeo.2020.104293

    work page doi:10.1016/j.marpetgeo.2020.104293 2020

  34. [34]

    W., Back, S., Urai, J

    Van Gent, H. W., Back, S., Urai, J. L., Kukla, P. A., & Reicherter, K. (2009). Paleostresses of the Groningen area, the Netherlands—Results of a seismic based structural reconstruction. Tectonophysics, 470(1-2), 147-161. https://doi.org/10.1016/j.tecto.2008.09.038

    work page doi:10.1016/j.tecto.2008.09.038 2009

  35. [35]

    TNO – GDN (2025) BRO DGM v2.2.1 TNO - Geological Survey of the Netherlands, https://www.dinoloket.nl/en/subsurface-models/map

    2025

  36. [36]

    P., Wiersma , A., Kloosterman , F

    Kruiver , P. P., Wiersma , A., Kloosterman , F. H., de Lange , G., Korff , M., Stafleu , J., Busschers , F. S., Harting , R., Gunnink , J. L., Green , R. A., van Elk , J., & Doornhof , D. (2018). Characterisation of the Groningen subsurface for seismic hazard and risk modelling. Netherlands Journal of Geosciences, 96, 215-233. https://doi.org/10.1017/njg.2017.11

    work page doi:10.1017/njg.2017.11 2018

  37. [37]

    S., van der Meulen, M

    Stafleu, J., Busschers, F. S., van der Meulen, M. J., Dulk, M. den, Gunnink, J. L., Maljers, D., Hummelman, J. H., Schokker, J., Vernes, R. W., Stam, J., Dabekaussen, W., Veen, J. H. ten, Doornenbal, H., Kars, R., & de Bruijn, R. (2025). Geological subsurface models of the Netherlands. In J. H. ten Veen, G.-J. Vis, J. de Jager, & T. E. Wong (Eds.), Geolog...

    work page doi:10.2307/jj.27435714.28 2025

  38. [38]

    Grigoratos, I., Bazzurro, P., Rathje, E., & Savvaidis, A. (2021). Time-dependent seismic hazard and risk due to wastewater injection in Oklahoma. Earthquake Spectra, 37(3), 2084–

    2021

  39. [39]

    https://doi.org/10.1177/8755293020988020

    work page doi:10.1177/8755293020988020

  40. [40]

    Limbeck, J., Bisdom, K., Lanz, F. et al. Using machine learning for model benchmarking and forecasting of depletion-induced seismicity in the Groningen gas field. Comput Geosci 25, 529–551 (2021). https://doi.org/10.1007/s10596-020-10023-0

    work page doi:10.1007/s10596-020-10023-0 2021

  41. [41]

    Baki, Z. (2025). Comprehensive monitoring and prediction of seismicity within the Groningen gas field using large-scale field observations. [PhD Thesis - Research UT, graduation UT, University of Twente]. University of Twente. https://doi.org/10.3990/1.9789036564908

    work page doi:10.3990/1.9789036564908 2025

  42. [42]

    Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 2242–2251). https://doi.org/10.1109/ICCV.2017.244

    work page doi:10.1109/iccv.2017.244 2017