Automated graptolite identification at high taxonomic resolution using residual networks
Summary: Graptolites, fossils significant for evolutionary studies and shale gas exploration, are traditionally identified visually by taxonomists due to their intricate morphologies and preservation challenges. Artificial intelligence (AI) holds great promise for transforming such meticulous tasks....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004223026263 |
| _version_ | 1797389426150604800 |
|---|---|
| author | Zhi-Bin Niu Si-Yuan Jia Hong-He Xu |
| author_facet | Zhi-Bin Niu Si-Yuan Jia Hong-He Xu |
| author_sort | Zhi-Bin Niu |
| collection | DOAJ |
| description | Summary: Graptolites, fossils significant for evolutionary studies and shale gas exploration, are traditionally identified visually by taxonomists due to their intricate morphologies and preservation challenges. Artificial intelligence (AI) holds great promise for transforming such meticulous tasks. In this paper, we demonstrate that graptolites can be identified with taxonomist accuracy using a deep learning model. We construct the most sophisticated and largest professional single organisms image dataset to date, which is composed of >34,000 images of 113 graptolite species annotated at pixel-level resolution to train the model, develop, and evaluate deep learning networks to classify graptolites. The model’s performance surpassed taxonomists in accuracy, time, and generalization, achieving 86% and 81% accuracy in identifying graptolite genus and species, respectively. This AI-based method, capable of recognizing minute morphological details better than taxonomists, can be integrated into web and mobile apps, extending graptolite identification beyond research institutes and enhancing shale gas exploration efficiency. |
| first_indexed | 2024-03-08T22:56:43Z |
| format | Article |
| id | doaj.art-973dddf119ba4e8fa98f1b0fc3030b8f |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-08T22:56:43Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-973dddf119ba4e8fa98f1b0fc3030b8f2023-12-16T06:08:46ZengElsevieriScience2589-00422024-01-01271108549Automated graptolite identification at high taxonomic resolution using residual networksZhi-Bin Niu0Si-Yuan Jia1Hong-He Xu2College of Intelligence and Computing, Tianjin University, Tianjin 300354, China; State Key Laboratory of Palaeobiology and Stratigraphy, Nanjing Institute of Geology and Palaeontology and Centre for Excellence in Life and Paleoenvironment, Chinese Academy of Sciences, Nanjing 210008, China; Corresponding authorCollege of Intelligence and Computing, Tianjin University, Tianjin 300354, ChinaState Key Laboratory of Palaeobiology and Stratigraphy, Nanjing Institute of Geology and Palaeontology and Centre for Excellence in Life and Paleoenvironment, Chinese Academy of Sciences, Nanjing 210008, China; Corresponding authorSummary: Graptolites, fossils significant for evolutionary studies and shale gas exploration, are traditionally identified visually by taxonomists due to their intricate morphologies and preservation challenges. Artificial intelligence (AI) holds great promise for transforming such meticulous tasks. In this paper, we demonstrate that graptolites can be identified with taxonomist accuracy using a deep learning model. We construct the most sophisticated and largest professional single organisms image dataset to date, which is composed of >34,000 images of 113 graptolite species annotated at pixel-level resolution to train the model, develop, and evaluate deep learning networks to classify graptolites. The model’s performance surpassed taxonomists in accuracy, time, and generalization, achieving 86% and 81% accuracy in identifying graptolite genus and species, respectively. This AI-based method, capable of recognizing minute morphological details better than taxonomists, can be integrated into web and mobile apps, extending graptolite identification beyond research institutes and enhancing shale gas exploration efficiency.http://www.sciencedirect.com/science/article/pii/S2589004223026263Earth sciencesGeologyPaleontologyArtificial intelligence |
| spellingShingle | Zhi-Bin Niu Si-Yuan Jia Hong-He Xu Automated graptolite identification at high taxonomic resolution using residual networks iScience Earth sciences Geology Paleontology Artificial intelligence |
| title | Automated graptolite identification at high taxonomic resolution using residual networks |
| title_full | Automated graptolite identification at high taxonomic resolution using residual networks |
| title_fullStr | Automated graptolite identification at high taxonomic resolution using residual networks |
| title_full_unstemmed | Automated graptolite identification at high taxonomic resolution using residual networks |
| title_short | Automated graptolite identification at high taxonomic resolution using residual networks |
| title_sort | automated graptolite identification at high taxonomic resolution using residual networks |
| topic | Earth sciences Geology Paleontology Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2589004223026263 |
| work_keys_str_mv | AT zhibinniu automatedgraptoliteidentificationathightaxonomicresolutionusingresidualnetworks AT siyuanjia automatedgraptoliteidentificationathightaxonomicresolutionusingresidualnetworks AT honghexu automatedgraptoliteidentificationathightaxonomicresolutionusingresidualnetworks |