Using Machine Learning to Predict Oil–Mineral Aggregates Formation
The formation of oil–mineral aggregates (OMAs) is essential for understanding the behavior of oil spills in estuaries and coastal waters. We utilized statistical methods (screening design) to identify the most influential variables (seven factors in total) during OMA formation. Time was the most imp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/12/1/144 |
| _version_ | 1797343314090917888 |
|---|---|
| author | Xiaomei Zhong Yongsheng Wu Jie Yu Lei Liu Haibo Niu |
| author_facet | Xiaomei Zhong Yongsheng Wu Jie Yu Lei Liu Haibo Niu |
| author_sort | Xiaomei Zhong |
| collection | DOAJ |
| description | The formation of oil–mineral aggregates (OMAs) is essential for understanding the behavior of oil spills in estuaries and coastal waters. We utilized statistical methods (screening design) to identify the most influential variables (seven factors in total) during OMA formation. Time was the most important factor, followed by temperature and oil/clay ratio. Moreover, machine learning was applied to predict the OMA median diameter (D<sub>50</sub>). Among the three tested algorithms, the Random Forest (RF) algorithm showed the highest accuracy, with a training R<sup>2</sup> of 0.99 and testing R<sup>2</sup> of 0.93. An open-source software tool that integrates the RF algorithm was developed, allowing users to easily estimate the OMA D<sub>50</sub> based on input variables. The valuable results and the practical tool we have developed enhance the understanding and management of environmental impacts associated with oil spills. |
| first_indexed | 2024-03-08T10:45:49Z |
| format | Article |
| id | doaj.art-f41ab67757854395902e181f650b1f4e |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-08T10:45:49Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-f41ab67757854395902e181f650b1f4e2024-01-26T17:17:10ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-01-0112114410.3390/jmse12010144Using Machine Learning to Predict Oil–Mineral Aggregates FormationXiaomei Zhong0Yongsheng Wu1Jie Yu2Lei Liu3Haibo Niu4Department of Civil and Resource Engineering, Faculty of Engineering, Dalhousie University, Halifax, NS B3H 4R2, CanadaFisheries and Oceans Canada, Bedford Institute of Oceanography, Dartmouth, NS B2Y 4A2, CanadaMechanical and Electrical Engineering Practice Center, Fuzhou University, Fuzhou 350108, ChinaDepartment of Civil and Resource Engineering, Faculty of Engineering, Dalhousie University, Halifax, NS B3H 4R2, CanadaDepartment of Engineering, Faculty of Agriculture, Dalhousie University, Truro, NS B2N 5E3, CanadaThe formation of oil–mineral aggregates (OMAs) is essential for understanding the behavior of oil spills in estuaries and coastal waters. We utilized statistical methods (screening design) to identify the most influential variables (seven factors in total) during OMA formation. Time was the most important factor, followed by temperature and oil/clay ratio. Moreover, machine learning was applied to predict the OMA median diameter (D<sub>50</sub>). Among the three tested algorithms, the Random Forest (RF) algorithm showed the highest accuracy, with a training R<sup>2</sup> of 0.99 and testing R<sup>2</sup> of 0.93. An open-source software tool that integrates the RF algorithm was developed, allowing users to easily estimate the OMA D<sub>50</sub> based on input variables. The valuable results and the practical tool we have developed enhance the understanding and management of environmental impacts associated with oil spills.https://www.mdpi.com/2077-1312/12/1/144oil–mineral aggregates (OMAs)machine learning algorithmsscreening designopen-source software |
| spellingShingle | Xiaomei Zhong Yongsheng Wu Jie Yu Lei Liu Haibo Niu Using Machine Learning to Predict Oil–Mineral Aggregates Formation Journal of Marine Science and Engineering oil–mineral aggregates (OMAs) machine learning algorithms screening design open-source software |
| title | Using Machine Learning to Predict Oil–Mineral Aggregates Formation |
| title_full | Using Machine Learning to Predict Oil–Mineral Aggregates Formation |
| title_fullStr | Using Machine Learning to Predict Oil–Mineral Aggregates Formation |
| title_full_unstemmed | Using Machine Learning to Predict Oil–Mineral Aggregates Formation |
| title_short | Using Machine Learning to Predict Oil–Mineral Aggregates Formation |
| title_sort | using machine learning to predict oil mineral aggregates formation |
| topic | oil–mineral aggregates (OMAs) machine learning algorithms screening design open-source software |
| url | https://www.mdpi.com/2077-1312/12/1/144 |
| work_keys_str_mv | AT xiaomeizhong usingmachinelearningtopredictoilmineralaggregatesformation AT yongshengwu usingmachinelearningtopredictoilmineralaggregatesformation AT jieyu usingmachinelearningtopredictoilmineralaggregatesformation AT leiliu usingmachinelearningtopredictoilmineralaggregatesformation AT haiboniu usingmachinelearningtopredictoilmineralaggregatesformation |