pith. machine review for the scientific record. sign in

arxiv: 2605.03919 · v1 · submitted 2026-05-05 · ⚛️ physics.geo-ph · cs.CC· cs.CV· physics.comp-ph

Recognition: unknown

Robustness and Transferability of Pix2Geomodel for Bidirectional Facies Property Translation in a Complex Reservoir

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

Pith reviewed 2026-05-07 00:40 UTC · model grok-4.3

classification ⚛️ physics.geo-ph cs.CCcs.CVphysics.comp-ph
keywords faciesreservoirporositybidirectionalcomplexmodelpermeabilitypix2geomodel
0
0 comments X

The pith

Pix2Pix-based Pix2Geomodel transfers to a stricter reservoir dataset while preserving dominant facies-property spatial patterns, with best performance on facies-to-porosity translation.

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

Reservoir models need to turn sparse well data into full 3D maps of rock type (facies) and properties such as porosity and permeability. Traditional statistics often miss the nonlinear links between these quantities. The authors take an existing image-to-image translation network called Pix2Pix, already used once on a simpler reservoir, and feed it paired 2-D slices from a harder case that has only 54 layers and more variable rock quality. They run six translation tasks in both directions and check the outputs with pixel accuracy, overlap scores, and variograms that measure spatial continuity. The model keeps the main geological shapes and trends, although performance drops on some property-to-facies tasks.

Core claim

Results show that the model preserves the dominant geological architecture and main spatial-continuity trends. Facies to porosity achieved the highest pixel accuracy and frequency-weighted intersection over union of 0.9326 and 0.8807.

Load-bearing premise

That 2-D slice pairs plus geometric augmentation sufficiently represent the 3-D heterogeneity and vertical connectivity of the target reservoir so that image metrics and variograms reliably indicate geological fidelity.

read the original abstract

Reservoir geomodeling is central to subsurface characterization, but it remains challenging because conditioning data are sparse, geological heterogeneity is strong, and conventional geostatistical workflows often struggle to capture nonlinear relationships between facies and petrophysical properties. This study evaluates the robustness and transferability of Pix2Geomodel on a different and more complex reservoir dataset with reduced vertical support. The new case includes a heterogeneous reservoir-quality classification and only 54 retained layers, providing a stricter test of whether Pix2Pix-based image-to-image translation can preserve facies-property relationships under constrained data conditions. Facies, porosity, permeability, and clay volume (VCL) were extracted from a reference reservoir model, exported as aligned two-dimensional slices, augmented using consistent geometric transformations, and assembled into paired image datasets. Six bidirectional tasks were evaluated: facies to porosity, facies to permeability, facies to VCL, porosity to facies, permeability to facies, and VCL to facies. The Pix2Pix model, consisting of a U-Net generator and PatchGAN discriminator, was evaluated using image-based metrics, visual comparison, and variogram-based spatial-continuity validation. Results show that the model preserves the dominant geological architecture and main spatial-continuity trends. Facies to porosity achieved the highest pixel accuracy and frequency-weighted intersection over union of 0.9326 and 0.8807, while VCL to facies achieved the highest mean pixel accuracy and mean intersection over union of 0.8506 and 0.7049. These findings show that Pix2Geomodel can transfer beyond its original case study as a practical framework for rapid bidirectional facies-property translation in complex reservoir modeling.

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.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the assumption that 2-D image metrics and variograms are sufficient proxies for 3-D geological fidelity; no new physical constants or entities are introduced.

axioms (1)
  • domain assumption Paired 2-D slices plus geometric augmentation preserve the statistical relationships needed for bidirectional facies-property translation.
    Invoked when the authors extract and augment slices from the reference model and treat them as representative training pairs.

pith-pipeline@v0.9.0 · 5619 in / 1310 out tokens · 21296 ms · 2026-05-07T00:40:17.931521+00:00 · methodology

discussion (0)

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