Pyrite (FeS₂) framboids, spheroidal groups of discrete equant pyrite microcrysts, are found in sediments of all geological ages. The size of a pyrite framboid is established during early diagenesis and preserved through time. Framboid size distributions are hence useful for the evaluation of depositional conditions. In this work, we present machine learning approaches to characterize the size distributions of pyrite framboids to understand the intensity and duration of anoxia and euxinia during the Middle Devonian of the Appalachian foreland basin by analyzing framboid size distributions of the Marcellus Shale from Lycoming County, Pennsylvania. Importantly, we overcome the time-consuming and laborious nature of current manual tracing methods to enable the processing of high volumes of micrograph data. Specifically, we implement convolutional neural networks (CNNs) to characterize framboids from 14 samples across depths in the Marcellus Shale. We show that CNNs enable the precise and fast measurement of framboid size distributions from scanning electron micrographs. CNN architectures including Inception, ResNet, Inception-Resnet, and Mask R-CNN were trained and tested on a total of ~6,800 framboids from 128 grayscale and 32 colored scanning electron micrographs. Kolmogorov-Smirnov tests on the framboidal equivalent diameter distributions measured from CNNs and manual tracing show that the CNN algorithms detected framboids with up to 99% precision. Importantly, once trained, the CNNs were ~100 times faster than current manual tracing. A straightforward extension of this work includes the application of CNNs to characterize pores, fractures, organic matter, and/or mineral grains in geological materials.

黄铁矿 (FeS ₂) framboids，离散的等离子黄铁矿微晶的球状群，在所有地质时代的沉积物中都有发现。黄铁矿的大小是在早期成岩作用中确定的，并随着时间的推移而保存下来。因此，Framboid 尺寸分布可用于评估沉积条件。在这项工作中，我们提出了机器学习方法来表征黄铁矿 framboids 的大小分布，通过分析宾夕法尼亚州莱康明县 Marcellus 页岩的 framboid 大小分布，了解阿巴拉契亚前陆盆地中泥盆纪期间缺氧和euxinia 的强度和持续时间. 重要的是，我们克服了当前手动追踪方法耗时费力的问题，能够处理大量显微照片数据。具体来说，我们实现了卷积神经网络 (CNN) 来表征来自 Marcellus 页岩中不同深度的 14 个样本的 framboid。我们表明，CNN 能够从扫描电子显微照片中精确、快速地测量 framboid 尺寸分布。包括 Inception、ResNet、Inception-Resnet 和 Mask R-CNN 在内的 CNN 架构在来自 128 个灰度和 32 个彩色扫描电子显微照片的总共约 6,800 个小方体上进行了训练和测试。Kolmogorov-Smirnov 对从 CNN 和手动跟踪测量的 framboidal 等效直径分布的测试表明，CNN 算法检测到 framboids 的精度高达 99%。重要的是，一旦经过训练，CNN 的速度比当前的手动跟踪快约 100 倍。这项工作的一个直接扩展包括应用 CNN 来表征孔隙、裂缝、有机质、