Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources
Machine learning provides solutions to a diverse range of problems in high-dimensional datasets in geosciences. However, machine learning is generally criticized for being an enigmatic black box as it focusses on results but ignores the processes. To address this issue, we used supervised decision b...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/13/4/491 |
| _version_ | 1797604156798664704 |
|---|---|
| author | Tong Zhou Yi-Wei Cai Mao-Guo An Fei Zhou Cheng-Long Zhi Xin-Chun Sun Murat Tamer |
| author_facet | Tong Zhou Yi-Wei Cai Mao-Guo An Fei Zhou Cheng-Long Zhi Xin-Chun Sun Murat Tamer |
| author_sort | Tong Zhou |
| collection | DOAJ |
| description | Machine learning provides solutions to a diverse range of problems in high-dimensional datasets in geosciences. However, machine learning is generally criticized for being an enigmatic black box as it focusses on results but ignores the processes. To address this issue, we used supervised decision boundary maps (SDBM) to visually illustrate and interpret the machine learning process. We constructed a SDBM to classify the ore genetics from 1551 trace element data of apatite in various types of deposits. Attribute-based visual explanation of multidimensional projections (A-MPs) was introduced to SDBM to further demonstrate the correlation between features and machine learning process. Our results show that SDBM explores the interpretability of machine learning process and the A-MPs approach reveals the role of trace elements in machine learning classification. Combining SDBM and A-MPs methods, we propose intuitive and accurate discrimination diagrams and the most indicative elements for ore genetic types. Our work provides novel insights for the visualization application of geo-machine learning, which is expected to be a powerful tool for high-dimensional geochemical data analysis and mineral deposit exploration. |
| first_indexed | 2024-03-11T04:42:23Z |
| format | Article |
| id | doaj.art-3ab66856aff740ee94cd5f7cfa5796be |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-11T04:42:23Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-3ab66856aff740ee94cd5f7cfa5796be2023-11-17T20:35:26ZengMDPI AGMinerals2075-163X2023-03-0113449110.3390/min13040491Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore SourcesTong Zhou0Yi-Wei Cai1Mao-Guo An2Fei Zhou3Cheng-Long Zhi4Xin-Chun Sun5Murat Tamer6State Key Laboratory of Geological Processes and Mineral Resources, School of Earth Science and Resources, China University of Geosciences, Beijing 100083, ChinaState Key Laboratory of Geological Processes and Mineral Resources, School of Earth Science and Resources, China University of Geosciences, Beijing 100083, ChinaState Key Laboratory of Geological Processes and Mineral Resources, School of Earth Science and Resources, China University of Geosciences, Beijing 100083, ChinaState Key Laboratory of Geological Processes and Mineral Resources, School of Earth Science and Resources, China University of Geosciences, Beijing 100083, ChinaShandong Provincial Lunan Geology and Exploration Institute, Shandong Provincial Bureau of Geology and Mineral Resources No.2 Geological Brigade, Jining 272100, ChinaGeological Survey of Gansu Province, Lanzhou 730000, ChinaState Key Laboratory of Earthquake Dynamics, Institute of Geology, China Earthquake Administration, Beijing 100029, ChinaMachine learning provides solutions to a diverse range of problems in high-dimensional datasets in geosciences. However, machine learning is generally criticized for being an enigmatic black box as it focusses on results but ignores the processes. To address this issue, we used supervised decision boundary maps (SDBM) to visually illustrate and interpret the machine learning process. We constructed a SDBM to classify the ore genetics from 1551 trace element data of apatite in various types of deposits. Attribute-based visual explanation of multidimensional projections (A-MPs) was introduced to SDBM to further demonstrate the correlation between features and machine learning process. Our results show that SDBM explores the interpretability of machine learning process and the A-MPs approach reveals the role of trace elements in machine learning classification. Combining SDBM and A-MPs methods, we propose intuitive and accurate discrimination diagrams and the most indicative elements for ore genetic types. Our work provides novel insights for the visualization application of geo-machine learning, which is expected to be a powerful tool for high-dimensional geochemical data analysis and mineral deposit exploration.https://www.mdpi.com/2075-163X/13/4/491apatitetrace elementore genetic typevisualizationSDBMA-MPs |
| spellingShingle | Tong Zhou Yi-Wei Cai Mao-Guo An Fei Zhou Cheng-Long Zhi Xin-Chun Sun Murat Tamer Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources Minerals apatite trace element ore genetic type visualization SDBM A-MPs |
| title | Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources |
| title_full | Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources |
| title_fullStr | Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources |
| title_full_unstemmed | Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources |
| title_short | Visual Interpretation of Machine Learning: Genetical Classification of Apatite from Various Ore Sources |
| title_sort | visual interpretation of machine learning genetical classification of apatite from various ore sources |
| topic | apatite trace element ore genetic type visualization SDBM A-MPs |
| url | https://www.mdpi.com/2075-163X/13/4/491 |
| work_keys_str_mv | AT tongzhou visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT yiweicai visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT maoguoan visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT feizhou visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT chenglongzhi visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT xinchunsun visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources AT murattamer visualinterpretationofmachinelearninggeneticalclassificationofapatitefromvariousoresources |