Title: Paw-Net: Stacking ensemble deep learning for segmenting scanning electron microscopy images of fine-grained shale samples

Abstract

Segmentation of scanning electron microscopy (SEM) images is critical yet time-consuming for geological analyses, as it needs to differentiate the boundaries for different mineral objects to facilitate subsequent analyses, such as porosity calculation. Recently, various machine learning methods, especially convolutional neural networks (CNNs), have been explored to segment SEM images of fine-grained shale samples. However, we found that general CNNs do not yield optimal performance due to insufficient training data and imbalanced objects in SEM images. This work has revised the U-Net architecture, a popular approach for biomedical image analyses, by incorporating a loss function that addresses the imbalance issue. Furthermore, we used the ensemble learning method to train multiple models and combined the results to improve the overall performance of segmentation. We prepared 2162 sub-images from raw SEM images in our experiments and divided them into training, validation, and testing datasets. The overall results show that our method improves the average Intersection over Union (IOU) of mineral objects from 0.49 to 0.58, compared to the original U-Net model. Our method can clearly distinguish each object from others with boundaries, even in highly imbalanced images. Training our models takes less than three minutes using a single GPU, while manual labelingmore » can take up to three hours for each image. Furthermore, the method helps geoscientists gain insights quickly and effectively by building neural network models from a small dataset of SEM images.« less

Authors:

Yin, Binqian ^[1]; Hu, Qinhong ^[1]; Zhu, Yingying ^[1]; Zhao, Chen ^[1]; Zhou, Keren ^[2]

---

+ Show Author Affiliations

1. Univ. of Texas, Arlington, TX (United States)
2. Rice Univ., Houston, TX (United States)

Publication Date:

Tue Aug 23 00:00:00 EDT 2022

Research Org.:

Univ. of Texas, Arlington, TX (United States)

Sponsoring Org.:

USDOE Office of Nuclear Energy (NE)

OSTI Identifier:

1894325

Alternate Identifier(s):

OSTI ID: 1884327

Grant/Contract Number:  

NE0008797

Resource Type:

Accepted Manuscript

Journal Name:

Computers and Geosciences

Additional Journal Information:

Journal Volume: 168; Journal ID: ISSN 0098-3004

Publisher:

Elsevier

Country of Publication:

United States

Language:

English

Subject:

58 GEOSCIENCES; Image segmentation; Neural network; Shale; Loss function; Ensemble learning; Imbalanced dataset