Multi-scale lithology recognition based on deep learning of rock images
Lithology recognition through artificial intelligence and big data can provide effective assistance to relevant personnel in field investigations.To better promote the application of lithology recognition in professional fields, the deep learning recognition of big data based on rock images were per...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Bulletin of Geological Science and Technology
2022-11-01
|
| Series: | 地质科技通报 |
| Subjects: | |
| Online Access: | https://dzkjqb.cug.edu.cn/en/article/doi/10.19509/j.cnki.dzkq.2022.0140 |
| _version_ | 1827330026937253888 |
|---|---|
| author | Zedong Ma Lei Ma Ke Li Wei Yao Peiding Wang Xinyu Wang |
| author_facet | Zedong Ma Lei Ma Ke Li Wei Yao Peiding Wang Xinyu Wang |
| author_sort | Zedong Ma |
| collection | DOAJ |
| description | Lithology recognition through artificial intelligence and big data can provide effective assistance to relevant personnel in field investigations.To better promote the application of lithology recognition in professional fields, the deep learning recognition of big data based on rock images were performed through the steps of rock image acquisition, data preprocessing, migration learning, network building, network training and model testing in the northern mountain area of Chaohu.Based on previous work, a multi-scale lithologic identification method is proposed. A multi-scale model is established and given a certain weight according to the rock meso image.The comprehensive results are obtained by identification with the rock identification model. The local texture, particle size and other mesoscale information were used in the overall identification of rock lithology.The results show that the multi-scale method is helpful to improve the identification results. The accuracy of the model is above 95%, which can well identify the rock lithology. |
| first_indexed | 2024-03-07T15:50:44Z |
| format | Article |
| id | doaj.art-d1ce592acb784b36ae82c21b0498be6c |
| institution | Directory Open Access Journal |
| issn | 2096-8523 |
| language | zho |
| last_indexed | 2024-03-07T15:50:44Z |
| publishDate | 2022-11-01 |
| publisher | Editorial Department of Bulletin of Geological Science and Technology |
| record_format | Article |
| series | 地质科技通报 |
| spelling | doaj.art-d1ce592acb784b36ae82c21b0498be6c2024-03-05T02:57:40ZzhoEditorial Department of Bulletin of Geological Science and Technology地质科技通报2096-85232022-11-0141631632210.19509/j.cnki.dzkq.2022.0140dzkjtb-41-6-316Multi-scale lithology recognition based on deep learning of rock imagesZedong Ma0Lei Ma1Ke Li2Wei Yao3Peiding Wang4Xinyu Wang5School of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaSchool of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, ChinaLithology recognition through artificial intelligence and big data can provide effective assistance to relevant personnel in field investigations.To better promote the application of lithology recognition in professional fields, the deep learning recognition of big data based on rock images were performed through the steps of rock image acquisition, data preprocessing, migration learning, network building, network training and model testing in the northern mountain area of Chaohu.Based on previous work, a multi-scale lithologic identification method is proposed. A multi-scale model is established and given a certain weight according to the rock meso image.The comprehensive results are obtained by identification with the rock identification model. The local texture, particle size and other mesoscale information were used in the overall identification of rock lithology.The results show that the multi-scale method is helpful to improve the identification results. The accuracy of the model is above 95%, which can well identify the rock lithology.https://dzkjqb.cug.edu.cn/en/article/doi/10.19509/j.cnki.dzkq.2022.0140deep learninglithology recognitionmulti-scaleweightimage |
| spellingShingle | Zedong Ma Lei Ma Ke Li Wei Yao Peiding Wang Xinyu Wang Multi-scale lithology recognition based on deep learning of rock images 地质科技通报 deep learning lithology recognition multi-scale weight image |
| title | Multi-scale lithology recognition based on deep learning of rock images |
| title_full | Multi-scale lithology recognition based on deep learning of rock images |
| title_fullStr | Multi-scale lithology recognition based on deep learning of rock images |
| title_full_unstemmed | Multi-scale lithology recognition based on deep learning of rock images |
| title_short | Multi-scale lithology recognition based on deep learning of rock images |
| title_sort | multi scale lithology recognition based on deep learning of rock images |
| topic | deep learning lithology recognition multi-scale weight image |
| url | https://dzkjqb.cug.edu.cn/en/article/doi/10.19509/j.cnki.dzkq.2022.0140 |
| work_keys_str_mv | AT zedongma multiscalelithologyrecognitionbasedondeeplearningofrockimages AT leima multiscalelithologyrecognitionbasedondeeplearningofrockimages AT keli multiscalelithologyrecognitionbasedondeeplearningofrockimages AT weiyao multiscalelithologyrecognitionbasedondeeplearningofrockimages AT peidingwang multiscalelithologyrecognitionbasedondeeplearningofrockimages AT xinyuwang multiscalelithologyrecognitionbasedondeeplearningofrockimages |