4.7 Article

Fossil brachiopod identification using a new deep convolutional neural network

期刊

GONDWANA RESEARCH
卷 105, 期 -, 页码 290-298

出版社

ELSEVIER
DOI: 10.1016/j.gr.2021.09.011

关键词

Fossil identification; Brachiopods; Deep learning; Convolution Neural Network; Transpose Convolutional Neural Network

资金

  1. National Natural Science Foundation [41702017, 41720104002, 41621003, 41890844]
  2. Science Foundation of China University of Petroleum (Beijing) [2462015YJRC015]
  3. State Key lab Petr. Resources Prospecting [PRP/indep-4-1521, PRP/indep-3-1811]
  4. Swedish Research Council (VR) [2018-03390]
  5. Department of Geology, Northwest University, Xi'an
  6. Swedish Research Council [2018-03390] Funding Source: Swedish Research Council

向作者/读者索取更多资源

The study introduces a new and efficient method for automatically identifying brachiopod fossils using a tailored Transpose Convolutional Neural Network (TCNN). Compared to the traditional Convolution Neural Network (CNN), the TCNN achieves higher identification accuracy on a smaller training dataset.
The identification of brachiopods requires specialist knowledge held by a limited number of researchers and is very time-consuming. The new technique of deep learning by artificial intelligence offers promising tools to break these shackles to develop computer automatic identification. However, we found that the traditional convolution neural network is not sufficient to automatically identify brachiopod species. Thus, we propose a new tailored Transpose Convolutional Neural Network (TCNN) in order to automatically identify brachiopod fossils with high efficiency. In this network, we add an upsampling Transpose Convolutional Layer and synthesize the data of this layer with the data of a Convolutional Layer to fully mix the small and large scales features extracted by the neural network. Compared with the traditional Convolution Neural Network (CNN), the Transpose Convolutional Neural Network (TCNN) can achieve a high identification accuracy using a smaller training data set of images of brachiopods. Results from this study show that the TCNN can achieve 98%, 98% and 97% identification accuracy respectively, with training data sets of 400 images of 3 species, 484 images of 4 species and 630 images of 5 species. In contrast, the traditional CNN can achieve only a low identification accuracy (67%) with 400 images of 3 species and requires 3000 images per 3 species to achieve a 95% identification accuracy. For most of brachiopod species, it is almost an impossible task to collected thousands of samples and as more brachiopod species are fitted into automatic identification, it is significant to have a reliable network which can achieve high accuracy on a small data set. In summary, the TCNN is a more efficient neural network that could be better applied to automatically identify brachiopod fossils. (C) 2021 International Association for Gondwana Research. Published by Elsevier B.V. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据