中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地质与地球物理研究所
  3. 中国科学院地质与地球物理研究所
  4. 中国科学院页岩气与地质工程重点实验室
Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin

文献类型：期刊论文

作者Chen, Zhuoheng2; Liu, Xiaojun2; Yang, Jijin1; Little, Edward2; Zhou, Yu
刊名COMPUTERS & GEOSCIENCES
出版日期2020-05-01
卷号138页码:10
关键词SEM image Deep learning Segmentation Mineral classification Nano-porosity
ISSN号0098-3004
DOI10.1016/j.cageo.2020.104450
英文摘要Texture-based feature extraction and object segmentation are challenging in image processing. In this study, the U-Net architecture developed for biomedical image analysis was used to evaluate geologic characteristics depicted within scanning electron microscope (SEM) images of shale samples. With a revised weight function, the U-Net architecture allowed for effective discrimination of clay aggregates mixed with matrix mineral particles and organic matter (OM). In training, a local variability weight based on spatial statistics was used to enhance the contrast between features across boundary in the loss function of U-Net system optimization, thereby improving the ability of U-Net to distinguish the geologic features specific to our research needs. The Tensorflow neural network library was used to create semantic segmentation and feature extraction models in mineral identification. In the application example of the Devonian Duvernay shale study, we prepared 8000 randomly sliced image cuts (256 x 256 pixels) from four masked image tiles (6144 x 6144 pixels) with tagged feature objects, among which 6400 are for training and the remaining 1600 held image slices for validation. In the validation, the average of intersection over union (IOU) reaches 91.7%. The trained model approved by validation was used for clay aggregate segmentation and mineral classification. Three hundred SEM image tiles of source rock samples from different maturities in the Duvernay Formation were processed using the proposed workflow. The results show that the clay aggregates are clearly separated from other matrix mineral particles with acceptable boundaries, although both exhibit indistinguishable grey-level pixels. This approach demonstrates that texture-based deep learning feature extraction is feasible, cost-effective and timely, and can help geoscientists gain new insights by quantitatively analyzing specific geological characteristics and features.
资助项目PERD (Program of Energy Research and Development) ; Natural Resources Canada ; Chinese National Major Fundamental Research Developing Project[2016ZX05034-0305]
WOS研究方向Computer Science ; Geology
语种英语
WOS记录号WOS:000526797800003
出版者PERGAMON-ELSEVIER SCIENCE LTD
资助机构PERD (Program of Energy Research and Development) ; PERD (Program of Energy Research and Development) ; Natural Resources Canada ; Natural Resources Canada ; Chinese National Major Fundamental Research Developing Project ; Chinese National Major Fundamental Research Developing Project ; PERD (Program of Energy Research and Development) ; PERD (Program of Energy Research and Development) ; Natural Resources Canada ; Natural Resources Canada ; Chinese National Major Fundamental Research Developing Project ; Chinese National Major Fundamental Research Developing Project ; PERD (Program of Energy Research and Development) ; PERD (Program of Energy Research and Development) ; Natural Resources Canada ; Natural Resources Canada ; Chinese National Major Fundamental Research Developing Project ; Chinese National Major Fundamental Research Developing Project ; PERD (Program of Energy Research and Development) ; PERD (Program of Energy Research and Development) ; Natural Resources Canada ; Natural Resources Canada ; Chinese National Major Fundamental Research Developing Project ; Chinese National Major Fundamental Research Developing Project
源URL[http://ir.iggcas.ac.cn/handle/132A11/95546]  
专题地质与地球物理研究所_中国科学院页岩气与地质工程重点实验室
通讯作者Chen, Zhuoheng
作者单位1.Chinese Acad Sci, Inst Geol & Geophys, Beijing, Peoples R China
2.Geol Survey Canada, 3303-33rd St NW, Calgary, AB T2L 2A7, Canada
推荐引用方式
GB/T 7714		 Chen, Zhuoheng,Liu, Xiaojun,Yang, Jijin,et al. Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin[J]. COMPUTERS & GEOSCIENCES,2020,138:10.
APA Chen, Zhuoheng,Liu, Xiaojun,Yang, Jijin,Little, Edward,&Zhou, Yu.(2020).Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin.COMPUTERS & GEOSCIENCES,138,10.
MLA Chen, Zhuoheng,et al."Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin".COMPUTERS & GEOSCIENCES 138(2020):10.

入库方式： OAI收割

来源：地质与地球物理研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。