PCP-GAN: Property-Constrained Pore-scale image reconstruction via conditional Generative Adversarial Networks

2025-10-22

AI Summary

Pore-scale image reconstruction suffers from representativeness deficiency due to spatial heterogeneity and sparse inter-well measurements. Method: This paper proposes a multi-conditional generative adversarial network (cGAN) framework that, for the first time, jointly enforces dual macroscopic physical constraints—porosity and depth—to enable high-fidelity, cross-stratigraphic pore-structure generation. The model integrates thin-section samples, morphology-aware loss functions, and multi-parameter conditional control to ensure both physical accuracy and structural realism. Contribution/Results: Experiments yield porosity prediction R² = 0.95 and MAE = 0.0099–0.0197; dual-constraint errors range only 1.9%–11.3%, substantially outperforming random sub-image sampling. The method establishes a new physically constrained, geologically interpretable paradigm for pore-scale characterization, with direct applicability to carbon sequestration, geothermal reservoir development, and groundwater management.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Obtaining truly representative pore-scale images that match bulk formation properties remains a fundamental challenge in subsurface characterization, as natural spatial heterogeneity causes extracted sub-images to deviate significantly from core-measured values. This challenge is compounded by data scarcity, where physical samples are only available at sparse well locations. This study presents a multi-conditional Generative Adversarial Network (cGAN) framework that generates representative pore-scale images with precisely controlled properties, addressing both the representativeness challenge and data availability constraints. The framework was trained on thin section samples from four depths (1879.50-1943.50 m) of a carbonate formation, simultaneously conditioning on porosity values and depth parameters within a single unified model. This approach captures both universal pore network principles and depth-specific geological characteristics, from grainstone fabrics with interparticle-intercrystalline porosity to crystalline textures with anhydrite inclusions. The model achieved exceptional porosity control (R^2=0.95) across all formations with mean absolute errors of 0.0099-0.0197. Morphological validation confirmed preservation of critical pore network characteristics including average pore radius, specific surface area, and tortuosity, with statistical differences remaining within acceptable geological tolerances. Most significantly, generated images demonstrated superior representativeness with dual-constraint errors of 1.9-11.3% compared to 36.4-578% for randomly extracted real sub-images. This capability provides transformative tools for subsurface characterization, particularly valuable for carbon storage, geothermal energy, and groundwater management applications where knowing the representative morphology of the pore space is critical for implementing digital rock physics.

Problem

• Generating representative pore-scale images matching bulk formation properties
• Addressing data scarcity from sparse physical sample locations
• Controlling porosity values and depth-specific geological characteristics simultaneously

Innovation

• Multi-conditional GAN generates pore-scale images with controlled properties
• Simultaneously conditions on porosity values and geological depth parameters
• Preserves critical pore network characteristics within geological tolerances