Department of Earth Sciences, Utrecht University, Utrecht, The Netherlands.
Materials Science and Engineering, Arizona State University, Tempe, USA.
Sci Rep. 2023 Jan 31;13(1):1805. doi: 10.1038/s41598-023-28970-w.
The key to most subsurface processes is to determine how structural and topological features at small length scales, i.e., the microstructure, control the effective and macroscopic properties of earth materials. Recent progress in imaging technology has enabled us to visualise and characterise microstructures at different length scales and dimensions. However, one limitation of these technologies is the trade-off between resolution and sample size (or representativeness). A promising approach to this problem is image reconstruction which aims to generate statistically equivalent microstructures but at a larger scale and/or additional dimension. In this work, a stochastic method and three generative adversarial networks (GANs), namely deep convolutional GAN (DCGAN), Wasserstein GAN with gradient penalty (WGAN-GP), and StyleGAN2 with adaptive discriminator augmentation (ADA), are used to reconstruct two-dimensional images of two hydrothermally rocks with varying degrees of complexity. For the first time, we evaluate and compare the performance of these methods using multi-point spatial correlation functions-known as statistical microstructural descriptors (SMDs)-ultimately used as external tools to the loss functions. Our findings suggest that a well-trained GAN can reconstruct higher-order, spatially-correlated patterns of complex earth materials, capturing underlying structural and morphological properties. Comparing our results with a stochastic reconstruction method based on a two-point correlation function, we show the importance of coupling training/assessment of GANs with higher-order SMDs, especially in the case of complex microstructures. More importantly, by quantifying original and reconstructed microstructures via different GANs, we highlight the interpretability of these SMDs and show how they can provide valuable insights into the spatial patterns in the synthetic images, allowing us to detect common artefacts and failure cases in training GANs.
大多数次表层过程的关键是确定小尺度结构和拓扑特征（即微观结构）如何控制地球材料的有效和宏观性质。成像技术的最新进展使我们能够在不同的尺度和维度上可视化和描述微观结构。然而，这些技术的一个局限性是分辨率和样品尺寸（或代表性）之间的权衡。解决这个问题的一种有前途的方法是图像重建，它旨在生成在更大尺度和/或附加维度上具有统计学等效的微观结构。在这项工作中，使用随机方法和三种生成对抗网络（GAN），即深度卷积 GAN（DCGAN）、带梯度惩罚的 Wasserstein GAN（WGAN-GP）和具有自适应判别器增强的 StyleGAN2（ADA），对两种具有不同复杂程度的水热岩石的二维图像进行重建。我们首次使用称为统计微观结构描述符（SMD）的多点空间相关函数来评估和比较这些方法的性能——最终将其用作损失函数的外部工具。我们的研究结果表明，经过良好训练的 GAN 可以重建复杂地球材料的高阶、空间相关模式，从而捕获其潜在的结构和形态特性。通过将基于两点相关函数的随机重建方法与 GAN 进行比较，我们展示了将 GAN 的训练/评估与高阶 SMD 相结合的重要性，特别是在复杂微观结构的情况下。更重要的是，通过使用不同的 GAN 对原始和重建的微观结构进行量化，我们突出了这些 SMD 的可解释性，并展示了它们如何为合成图像中的空间模式提供有价值的见解，使我们能够检测到训练 GAN 中的常见人工制品和失败案例。
