Development of a short-term water quality prediction model for urban rivers using real-time water quality data
We developed a classification model and a real-time prediction model for short-term dissolved oxygen (DO) at the junction of the Han River in Anyangcheon, where water quality accidents occur frequently. The classification model is an analysis model that derives the main factors affecting DO changes...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2022-04-01
|
| Series: | Water Supply |
| Subjects: | |
| Online Access: | http://ws.iwaponline.com/content/22/4/4082 |
| _version_ | 1811309002458398720 |
|---|---|
| author | J. H. Lee J. Y. Lee M. H. Lee M. Y. Lee Y. W. Kim J. S. Hyung K. B. Kim Y. K. Cha J. Y. Koo |
| author_facet | J. H. Lee J. Y. Lee M. H. Lee M. Y. Lee Y. W. Kim J. S. Hyung K. B. Kim Y. K. Cha J. Y. Koo |
| author_sort | J. H. Lee |
| collection | DOAJ |
| description | We developed a classification model and a real-time prediction model for short-term dissolved oxygen (DO) at the junction of the Han River in Anyangcheon, where water quality accidents occur frequently. The classification model is an analysis model that derives the main factors affecting DO changes in the Anyangcheon mobile water quality monitoring network using decision tree, random forest, and XGBoost. The model identified the key factors affecting DO changes to be electrical conductivity, cumulative precipitation, total nitrogen, and water temperature. Random forest (sensitivity, 0.9962; accuracy, 0.9981) and XGBoost (sensitivity, 1.0000; accuracy, 0.9822) showed excellent classification performance. The real-time prediction model for short-term DO that we developed adopted artificial neural network (ANN), long short-term memory (LSTM), and gated recurrent unit (GRU) algorithms. LSTM (R2 = 0.93 − 0.97, first half; R2 = 0.95 − 0.96, second half) and GRU (R2 = 0.94 − 0.98, first half; R2 = 0.96 − 0.98, second half) significantly outperformed ANN (R2 = 0.64 − 0.86). The LSTM and GRU models we developed used real-time automatic measurement data, targeting urban rivers that are sensitive to water quality changes and are waterfront areas for citizens. They can quickly reflect and simulate short-term, real-time changes in water quality compared with existing static models. HIGHLIGHTS
We developed a classification model and a real-time prediction model on urban rivers.;
The classification model identified the key factors affecting DO changes.;
The LSTM and GRU models can quickly reflect and simulate short-term, real-time changes in water quality.;
The dissolved oxygen water quality prediction model developed in this study is an ensemble model grafted with a classification model.; |
| first_indexed | 2024-04-13T09:34:32Z |
| format | Article |
| id | doaj.art-7b93176bf0d64ce59f32b9a92fd58e3a |
| institution | Directory Open Access Journal |
| issn | 1606-9749 1607-0798 |
| language | English |
| last_indexed | 2024-04-13T09:34:32Z |
| publishDate | 2022-04-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Supply |
| spelling | doaj.art-7b93176bf0d64ce59f32b9a92fd58e3a2022-12-22T02:52:09ZengIWA PublishingWater Supply1606-97491607-07982022-04-012244082409710.2166/ws.2022.038038Development of a short-term water quality prediction model for urban rivers using real-time water quality dataJ. H. Lee0J. Y. Lee1M. H. Lee2M. Y. Lee3Y. W. Kim4J. S. Hyung5K. B. Kim6Y. K. Cha7J. Y. Koo8 Department of Water Environment Research, Seoul Metropolitan Government Research Institute of Public Health and Environment, Seoul 13818, Korea Department of Water Environment Research, Seoul Metropolitan Government Research Institute of Public Health and Environment, Seoul 13818, Korea Department of Water Environment Research, Seoul Metropolitan Government Research Institute of Public Health and Environment, Seoul 13818, Korea Department of Water Environment Research, Seoul Metropolitan Government Research Institute of Public Health and Environment, Seoul 13818, Korea School of Environmental Engineering, University of Seoul, Seoul 02504, Korea Construction Engineering and Management, Purdue University, Indiana, USA Construction Engineering and Management, Purdue University, Indiana, USA School of Environmental Engineering, University of Seoul, Seoul 02504, Korea School of Environmental Engineering, University of Seoul, Seoul 02504, Korea We developed a classification model and a real-time prediction model for short-term dissolved oxygen (DO) at the junction of the Han River in Anyangcheon, where water quality accidents occur frequently. The classification model is an analysis model that derives the main factors affecting DO changes in the Anyangcheon mobile water quality monitoring network using decision tree, random forest, and XGBoost. The model identified the key factors affecting DO changes to be electrical conductivity, cumulative precipitation, total nitrogen, and water temperature. Random forest (sensitivity, 0.9962; accuracy, 0.9981) and XGBoost (sensitivity, 1.0000; accuracy, 0.9822) showed excellent classification performance. The real-time prediction model for short-term DO that we developed adopted artificial neural network (ANN), long short-term memory (LSTM), and gated recurrent unit (GRU) algorithms. LSTM (R2 = 0.93 − 0.97, first half; R2 = 0.95 − 0.96, second half) and GRU (R2 = 0.94 − 0.98, first half; R2 = 0.96 − 0.98, second half) significantly outperformed ANN (R2 = 0.64 − 0.86). The LSTM and GRU models we developed used real-time automatic measurement data, targeting urban rivers that are sensitive to water quality changes and are waterfront areas for citizens. They can quickly reflect and simulate short-term, real-time changes in water quality compared with existing static models. HIGHLIGHTS We developed a classification model and a real-time prediction model on urban rivers.; The classification model identified the key factors affecting DO changes.; The LSTM and GRU models can quickly reflect and simulate short-term, real-time changes in water quality.; The dissolved oxygen water quality prediction model developed in this study is an ensemble model grafted with a classification model.;http://ws.iwaponline.com/content/22/4/4082classification modeldissolved oxygen prediction modelreal-time automatic measurement dataurban riverwater quality accident |
| spellingShingle | J. H. Lee J. Y. Lee M. H. Lee M. Y. Lee Y. W. Kim J. S. Hyung K. B. Kim Y. K. Cha J. Y. Koo Development of a short-term water quality prediction model for urban rivers using real-time water quality data Water Supply classification model dissolved oxygen prediction model real-time automatic measurement data urban river water quality accident |
| title | Development of a short-term water quality prediction model for urban rivers using real-time water quality data |
| title_full | Development of a short-term water quality prediction model for urban rivers using real-time water quality data |
| title_fullStr | Development of a short-term water quality prediction model for urban rivers using real-time water quality data |
| title_full_unstemmed | Development of a short-term water quality prediction model for urban rivers using real-time water quality data |
| title_short | Development of a short-term water quality prediction model for urban rivers using real-time water quality data |
| title_sort | development of a short term water quality prediction model for urban rivers using real time water quality data |
| topic | classification model dissolved oxygen prediction model real-time automatic measurement data urban river water quality accident |
| url | http://ws.iwaponline.com/content/22/4/4082 |
| work_keys_str_mv | AT jhlee developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT jylee developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT mhlee developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT mylee developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT ywkim developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT jshyung developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT kbkim developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT ykcha developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata AT jykoo developmentofashorttermwaterqualitypredictionmodelforurbanriversusingrealtimewaterqualitydata |