Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea
Abstracts: Study region: Euiam Lake in the Republic of Korea Study focus: This study establishes a framework to prioritize total phosphorus (TP) management strategies based on machine learning (ML). A comparative analysis is conducted to evaluate the performance of four ML methods: random forest (R...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Journal of Hydrology: Regional Studies |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214581822000829 |
| _version_ | 1811336579361275904 |
|---|---|
| author | Hye Won Lee Min Kim Hee Won Son Baehyun Min Jung Hyun Choi |
| author_facet | Hye Won Lee Min Kim Hee Won Son Baehyun Min Jung Hyun Choi |
| author_sort | Hye Won Lee |
| collection | DOAJ |
| description | Abstracts: Study region: Euiam Lake in the Republic of Korea Study focus: This study establishes a framework to prioritize total phosphorus (TP) management strategies based on machine learning (ML). A comparative analysis is conducted to evaluate the performance of four ML methods: random forest (RF), extreme gradient boosting (XGBoost), deep neural network (DNN), and long short-term memory (LSTM). The LSTM-based model is selected as the optimal predictive model of TP concentration in Euiam Lake (E_TP) on seasons (May to October) with high rainfall and inflow from two upstream dams (Chuncheon Dam and Soyanggang Dam). We also perform a gradient-based analysis to figure out the most influential factors on E_TP using the LSTM model. The top four priority factors are TP concentrations and suspended solids concentrations in the upstream dams. This application of the gradient-based analysis enables the predictive model to discuss quantitative reductions in the priorities. Based on these numerical results, we anticipate that the proposed framework can enhance the feasibility of management practices for achieving the water quality management goal of the study region. New hydrological insights: This study demonstrates that a robust predictive model can be developed for a serial impoundment system with distinct seasonal characteristics of rainfall, temperature, and water quality, thereby facilitating the selection of management priorities. Based on the predictive model results, we conclude that it is the key for managing the target TP concentration to prioritize the incoming TP concentrations and determine the quantitative |
| first_indexed | 2024-04-13T17:41:27Z |
| format | Article |
| id | doaj.art-72ef4f61cad4418f8982cf8d2832f6e4 |
| institution | Directory Open Access Journal |
| issn | 2214-5818 |
| language | English |
| last_indexed | 2024-04-13T17:41:27Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Hydrology: Regional Studies |
| spelling | doaj.art-72ef4f61cad4418f8982cf8d2832f6e42022-12-22T02:37:10ZengElsevierJournal of Hydrology: Regional Studies2214-58182022-06-0141101069Machine-learning-based water quality management of river with serial impoundments in the Republic of KoreaHye Won Lee0Min Kim1Hee Won Son2Baehyun Min3Jung Hyun Choi4Center for Climate/Environment Change Prediction Research, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea; Department of Environmental Science and Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of KoreaSevere Storm Research Center, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of KoreaDepartment of Environmental Science and Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of KoreaCenter for Climate/Environment Change Prediction Research, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea; Department of Climate and Energy Systems Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea; Corresponding authors at: Center for Climate/Environment Change Prediction Research, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea.Center for Climate/Environment Change Prediction Research, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea; Department of Environmental Science and Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea; Corresponding authors at: Center for Climate/Environment Change Prediction Research, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760 Republic of Korea.Abstracts: Study region: Euiam Lake in the Republic of Korea Study focus: This study establishes a framework to prioritize total phosphorus (TP) management strategies based on machine learning (ML). A comparative analysis is conducted to evaluate the performance of four ML methods: random forest (RF), extreme gradient boosting (XGBoost), deep neural network (DNN), and long short-term memory (LSTM). The LSTM-based model is selected as the optimal predictive model of TP concentration in Euiam Lake (E_TP) on seasons (May to October) with high rainfall and inflow from two upstream dams (Chuncheon Dam and Soyanggang Dam). We also perform a gradient-based analysis to figure out the most influential factors on E_TP using the LSTM model. The top four priority factors are TP concentrations and suspended solids concentrations in the upstream dams. This application of the gradient-based analysis enables the predictive model to discuss quantitative reductions in the priorities. Based on these numerical results, we anticipate that the proposed framework can enhance the feasibility of management practices for achieving the water quality management goal of the study region. New hydrological insights: This study demonstrates that a robust predictive model can be developed for a serial impoundment system with distinct seasonal characteristics of rainfall, temperature, and water quality, thereby facilitating the selection of management priorities. Based on the predictive model results, we conclude that it is the key for managing the target TP concentration to prioritize the incoming TP concentrations and determine the quantitativehttp://www.sciencedirect.com/science/article/pii/S2214581822000829Machine learning (ML)Water qualitySerial impoundmentLong short-term memory (LSTM)Gradient-based analysis |
| spellingShingle | Hye Won Lee Min Kim Hee Won Son Baehyun Min Jung Hyun Choi Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea Journal of Hydrology: Regional Studies Machine learning (ML) Water quality Serial impoundment Long short-term memory (LSTM) Gradient-based analysis |
| title | Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea |
| title_full | Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea |
| title_fullStr | Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea |
| title_full_unstemmed | Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea |
| title_short | Machine-learning-based water quality management of river with serial impoundments in the Republic of Korea |
| title_sort | machine learning based water quality management of river with serial impoundments in the republic of korea |
| topic | Machine learning (ML) Water quality Serial impoundment Long short-term memory (LSTM) Gradient-based analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2214581822000829 |
| work_keys_str_mv | AT hyewonlee machinelearningbasedwaterqualitymanagementofriverwithserialimpoundmentsintherepublicofkorea AT minkim machinelearningbasedwaterqualitymanagementofriverwithserialimpoundmentsintherepublicofkorea AT heewonson machinelearningbasedwaterqualitymanagementofriverwithserialimpoundmentsintherepublicofkorea AT baehyunmin machinelearningbasedwaterqualitymanagementofriverwithserialimpoundmentsintherepublicofkorea AT junghyunchoi machinelearningbasedwaterqualitymanagementofriverwithserialimpoundmentsintherepublicofkorea |