Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data
Water environment pollution due to chemical spills occurs constantly worldwide. When a chemical accident occurs, a quick initial response is most important. In previous studies, samples collected from chemical accident sites were subjected to laboratory-based precise analysis or predictive research...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Toxics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2305-6304/11/4/314 |
| _version_ | 1797603348567818240 |
|---|---|
| author | Su Han Nam Jae Hyun Kwon Young Do Kim |
| author_facet | Su Han Nam Jae Hyun Kwon Young Do Kim |
| author_sort | Su Han Nam |
| collection | DOAJ |
| description | Water environment pollution due to chemical spills occurs constantly worldwide. When a chemical accident occurs, a quick initial response is most important. In previous studies, samples collected from chemical accident sites were subjected to laboratory-based precise analysis or predictive research through modeling. These results can be used to formulate appropriate responses in the event of chemical accidents; however, there are limitations to this process. For the initial response, it is important to quickly acquire information on chemicals leaked from the site. In this study, pH and electrical conductivity (EC), which are easy to measure in the field, were applied. In addition, 13 chemical substances were selected, and pH and EC data for each were established according to concentration change. The obtained data were applied to machine learning algorithms, including decision trees, random forests, gradient boosting, and XGBoost (XGB), to determine the chemical substances present. Through performance evaluation, the boosting method was found to be sufficient, and XGB was the most suitable algorithm for chemical substance detection. |
| first_indexed | 2024-03-11T04:27:55Z |
| format | Article |
| id | doaj.art-3a0416d098ad470aa457237be649351f |
| institution | Directory Open Access Journal |
| issn | 2305-6304 |
| language | English |
| last_indexed | 2024-03-11T04:27:55Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Toxics |
| spelling | doaj.art-3a0416d098ad470aa457237be649351f2023-11-17T21:37:06ZengMDPI AGToxics2305-63042023-03-0111431410.3390/toxics11040314Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring DataSu Han Nam0Jae Hyun Kwon1Young Do Kim2Department of Civil & Environmental Engineering, Myongji University, Yongin 17058, Republic of KoreaDepartment of Civil and Environmental Engineering, Nakdong River Basin Environmental Research Center, Inje University, Gimhae 50834, Republic of KoreaDepartment of Civil & Environmental Engineering, Myongji University, Yongin 17058, Republic of KoreaWater environment pollution due to chemical spills occurs constantly worldwide. When a chemical accident occurs, a quick initial response is most important. In previous studies, samples collected from chemical accident sites were subjected to laboratory-based precise analysis or predictive research through modeling. These results can be used to formulate appropriate responses in the event of chemical accidents; however, there are limitations to this process. For the initial response, it is important to quickly acquire information on chemicals leaked from the site. In this study, pH and electrical conductivity (EC), which are easy to measure in the field, were applied. In addition, 13 chemical substances were selected, and pH and EC data for each were established according to concentration change. The obtained data were applied to machine learning algorithms, including decision trees, random forests, gradient boosting, and XGBoost (XGB), to determine the chemical substances present. Through performance evaluation, the boosting method was found to be sufficient, and XGB was the most suitable algorithm for chemical substance detection.https://www.mdpi.com/2305-6304/11/4/314machine learningchemical contaminationalternative indicatorinitial responsechemical detection |
| spellingShingle | Su Han Nam Jae Hyun Kwon Young Do Kim Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data Toxics machine learning chemical contamination alternative indicator initial response chemical detection |
| title | Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data |
| title_full | Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data |
| title_fullStr | Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data |
| title_full_unstemmed | Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data |
| title_short | Comparison of Optimal Machine Learning Algorithms for Early Detection of Unknown Hazardous Chemicals in Rivers Using Sensor Monitoring Data |
| title_sort | comparison of optimal machine learning algorithms for early detection of unknown hazardous chemicals in rivers using sensor monitoring data |
| topic | machine learning chemical contamination alternative indicator initial response chemical detection |
| url | https://www.mdpi.com/2305-6304/11/4/314 |
| work_keys_str_mv | AT suhannam comparisonofoptimalmachinelearningalgorithmsforearlydetectionofunknownhazardouschemicalsinriversusingsensormonitoringdata AT jaehyunkwon comparisonofoptimalmachinelearningalgorithmsforearlydetectionofunknownhazardouschemicalsinriversusingsensormonitoringdata AT youngdokim comparisonofoptimalmachinelearningalgorithmsforearlydetectionofunknownhazardouschemicalsinriversusingsensormonitoringdata |