Sea Water Quality Estimation Using Machine Learning Algorithms
| Autor: | Haeng Yeol Oh, Minkyo Youm, Seung-Bae Jeon, Tae-Young Lee, Gun Kim, Myeong-Hun Jeong |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Estimation
Ecology business.industry media_common.quotation_subject Network data Machine learning computer.software_genre Random forest Support vector machine Environmental science Seawater Quality (business) Artificial intelligence Water quality business Algorithm computer Integrated management Earth-Surface Processes Water Science and Technology media_common |
| Zdroj: | Journal of Coastal Research. 114 |
| ISSN: | 0749-0208 |
| Popis: | Oh, H.Y.; Jeong, M.-H.; Jeon, S.B.; Lee, T.Y.; Kim, G., and Youm, M., 2021. Sea water quality estimation using machine learning algorithms. In: Lee, J.L.; Suh, K.-S.; Lee, B.; Shin, S.; and Lee, J. (eds.), Crisis and Integrated Management for Coastal and Marine Safety. Journal of Coastal Research, Special Issue No. 114, pp. 424–428. Coconut Creek (Florida), ISSN 0749-0208. The water quality index (WQI) determines the quality of drinking water and seawater. Currently, coastal and seawater quality is monitored and managed by classifying it into five grades based on the WQI value in the Republic of Korea. The Korea Marine Environment Management Corporation (KOEM) utilizes automatic environmental sensor networks to monitor the coastal environment. However, these sensor data do not include the essential variables for determining the water quality level. The KOEM manually evaluates the WQI four days per year. This study estimates the water quality level using machine-learning algorithms based on the measurements of the automatic environmental sensor network data. The experiments show that random forest and support vector machine algorithms perform better than other algorithms. The results of this study can be applied to monitor and predict water quality in real time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|