Pix2Geomodel: A next-generation reservoir geomodeling with property-to-property translation

Accurate geological modeling is essential for reservoir characterization, yet traditional methods struggle with complex subsurface heterogeneity and the conditioning of data to observed values. This study introduces Pix2Geomodel, a novel conditional generative adversarial network (cGAN) framework based on the Pix2Pix architecture, designed to predict key 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), and frequency-weighted intersection over union (FWIoU). Performance was evaluated in two tasks: (i) masked property prediction and (ii) property-to-property translation. 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 transferability performance (e.g., facies-to-Sw 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 provides more accurate and more time- and resource-efficient property mapping. While the current model is trained to perform 2D geomodeling, future work will be developed to involve 3D geomodeling and also consider microstructural heterogeneity in the geology of the area, with extensions to multi-modal inputs planned for Pix2Geomodel v2.0. This study advances the application of generative AI in geoscience, supporting improved reservoir management and open science initiatives. • Pix2Geomodel: the first Pix2Pix cGAN for reservoir property translation. • Handles both missing-data reconstruction and cross-property prediction. • Achieves high accuracy across multiple reservoir properties. • Preserves geological realism, validated by variograms, error metrics, and expert reviews. • Scalable workflow: ∼ 90 % faster, enabling future 3D applications. • Open-source datasets and code ensure reproducibility and reuse.