Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation

2025-06-21

AI Summary

Traditional geological modeling struggles to represent complex subsurface heterogeneity and integrate multi-source observational data under conditional constraints. To address this, we propose Pix2Geomodel—the first conditional generative adversarial network (cGAN) framework for joint reservoir property modeling, enabling image-to-image translation across multiple attributes: lithofacies, porosity, permeability, and water saturation. Our method employs a U-Net generator and a PatchGAN discriminator, augmented by variogram-guided data augmentation and pixel-level evaluation metrics (Pixel Accuracy, mIoU, FWIoU). Experiments demonstrate high predictive accuracy: lithofacies and water saturation predictions achieve 0.88 and 0.96 Pixel Accuracy, respectively; cross-attribute translation (e.g., lithofacies→lithofacies) reaches 0.98 Pixel Accuracy—substantially outperforming conventional approaches. Pix2Geomodel thus establishes the first high-fidelity, conditionally controllable framework for multi-attribute collaborative geological modeling.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• Predicts reservoir properties using generative adversarial networks
• Addresses challenges in modeling complex subsurface heterogeneity
• Improves accuracy in direct property mapping for reservoirs

Innovation

• Uses cGAN framework for reservoir property prediction
• Trains with U-Net generator and PatchGAN discriminator
• Achieves high accuracy in property-to-property translation