Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation
Not on the map. Why?
Abstract (arXiv)
Accurate geological modeling is critical for reservoir characterization, yet traditional methods struggle with complex subsurface heterogeneity, and they have problems with conditioning to observed data. This study introduces Pix2Geomodel, a novel conditional generative adversarial network (cGAN) framework based on Pix2Pix, designed to predict reservoir properties (facies, porosity, permeability, and water saturation) from the Rotliegend reservoir of the Groningen gas field. Utilizing a 7.6 million-cell dataset from the Nederlandse Aardolie Maatschappij, accessed via EPOS-NL, the methodology included data preprocessing, augmentation to generate 2,350 images per property, and training with a U-Net generator and PatchGAN discriminator over 19,000 steps. Evaluation metrics include pixel accuracy (PA), mean intersection over union (mIoU), frequency weighted intersection over union (FWIoU), and visualizations assessed performance in masked property prediction and property-to-property translation tasks. Results demonstrated high accuracy for facies (PA 0.88, FWIoU 0.85) and water saturation (PA 0.96, FWIoU 0.95), with moderate success for porosity (PA 0.70, FWIoU 0.55) and permeability (PA 0.74, FWIoU 0.60), and robust translation performance (e.g., facies-to-facies PA 0.98, FWIoU 0.97). The framework captured spatial variability and geological realism, as validated by variogram analysis, and calculated the training loss curves for the generator and discriminator for each property. Compared to traditional methods, Pix2Geomodel offers enhanced fidelity in direct property mapping. Limitations include challenges with microstructural variability and 2D constraints, suggesting future integration of multi-modal data and 3D modeling (Pix2Geomodel v2.0). This study advances the application of generative AI in geoscience, supporting improved reservoir management and open science initiatives.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 11 of its 81 references that are in the map. First posted on arXiv 21 Jun 2025.
Builds on
11 of 81 references.
References · 11
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2015Holistically-Nested Edge Detectioncited by 592
- 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
- 2017Reconstruction of three-dimensional porous media using generative adversarial neural networkscited by 36
- 2018Parametric generation of conditional geological realizations using generative neural networkscited by 19
- 2024Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translationcited by 7
- 2019DeepFlow: History Matching in the Space of Deep Generative Modelscited by 4
- 2018Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale modelscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.