Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy
Chemical oxygen demand (COD) is one of the indicators used to monitor the level of pollution in surface water. To recycle agricultural water resources, it is crucial to monitor, in a timely manner, whether COD in surface water exceeds the agricultural water control standard. A diagnostic model of su...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/14/19/3003 |
| _version_ | 1797476504854069248 |
|---|---|
| author | Xueqin Han Xiaoyan Chen Jinfang Ma Jiaze Chen Baiheng Xie Wenhua Yin Yanyan Yang Wenchao Jia Danping Xie Furong Huang |
| author_facet | Xueqin Han Xiaoyan Chen Jinfang Ma Jiaze Chen Baiheng Xie Wenhua Yin Yanyan Yang Wenchao Jia Danping Xie Furong Huang |
| author_sort | Xueqin Han |
| collection | DOAJ |
| description | Chemical oxygen demand (COD) is one of the indicators used to monitor the level of pollution in surface water. To recycle agricultural water resources, it is crucial to monitor, in a timely manner, whether COD in surface water exceeds the agricultural water control standard. A diagnostic model of surface water pollution was developed using visible near-infrared spectroscopy (Vis-NIR) combined with partial least squares discriminant analysis (PLS–DA). A total of 127 surface water samples were collected from Guangzhou, Guangdong, China. The COD content was measured using the potassium dichromate method. The spectra of the surface water samples were recorded using a Vis-NIR spectrometer, and the spectral data were pre-processed using four different methods. To improve the accuracy and simplicity of the model, the synthetic minority oversampling technique (SMOTE) and the competitive adaptive reweighted sampling (CARS) algorithm were used to enhance model performance. The best PLS–DA model achieved an accuracy of 88%, and the SMOTE–PLS–DA model had an accuracy of 94%. The SMOTE algorithm could improve the accuracy of the model despite the sampling imbalance. The CARS–SMOTE–PLS–DA model achieved 97% accuracy, and the CARS band selection technique improved the simplicity and accuracy of the discrimination model. The CARS–SMOTE–PLS–DA model improved the discrimination accuracy by 9% over that of the PLS–DA model. This method can not only save human and material resources but is also a new way for real-time online discrimination of COD in surface water. |
| first_indexed | 2024-03-09T20:59:47Z |
| format | Article |
| id | doaj.art-dcb2ab9cf0394b3a8dd411967f34a787 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T20:59:47Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-dcb2ab9cf0394b3a8dd411967f34a7872023-11-23T22:14:09ZengMDPI AGWater2073-44412022-09-011419300310.3390/w14193003Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared SpectroscopyXueqin Han0Xiaoyan Chen1Jinfang Ma2Jiaze Chen3Baiheng Xie4Wenhua Yin5Yanyan Yang6Wenchao Jia7Danping Xie8Furong Huang9Opto-Electronic Department, Jinan University, Guangzhou 510632, ChinaState Environment Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, ChinaOpto-Electronic Department, Jinan University, Guangzhou 510632, ChinaOpto-Electronic Department, Jinan University, Guangzhou 510632, ChinaOpto-Electronic Department, Jinan University, Guangzhou 510632, ChinaState Environment Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, ChinaState Environment Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, ChinaState Environment Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, ChinaState Environment Protection Key Laboratory of Water Environmental Simulation and Pollution Control, South China Institute of Environmental Sciences, Ministry of Ecology and Environment, Guangzhou 510655, ChinaOpto-Electronic Department, Jinan University, Guangzhou 510632, ChinaChemical oxygen demand (COD) is one of the indicators used to monitor the level of pollution in surface water. To recycle agricultural water resources, it is crucial to monitor, in a timely manner, whether COD in surface water exceeds the agricultural water control standard. A diagnostic model of surface water pollution was developed using visible near-infrared spectroscopy (Vis-NIR) combined with partial least squares discriminant analysis (PLS–DA). A total of 127 surface water samples were collected from Guangzhou, Guangdong, China. The COD content was measured using the potassium dichromate method. The spectra of the surface water samples were recorded using a Vis-NIR spectrometer, and the spectral data were pre-processed using four different methods. To improve the accuracy and simplicity of the model, the synthetic minority oversampling technique (SMOTE) and the competitive adaptive reweighted sampling (CARS) algorithm were used to enhance model performance. The best PLS–DA model achieved an accuracy of 88%, and the SMOTE–PLS–DA model had an accuracy of 94%. The SMOTE algorithm could improve the accuracy of the model despite the sampling imbalance. The CARS–SMOTE–PLS–DA model achieved 97% accuracy, and the CARS band selection technique improved the simplicity and accuracy of the discrimination model. The CARS–SMOTE–PLS–DA model improved the discrimination accuracy by 9% over that of the PLS–DA model. This method can not only save human and material resources but is also a new way for real-time online discrimination of COD in surface water.https://www.mdpi.com/2073-4441/14/19/3003surface watervis-NIR spectroscopychemical oxygen demandSMOTECARSPLS–DA |
| spellingShingle | Xueqin Han Xiaoyan Chen Jinfang Ma Jiaze Chen Baiheng Xie Wenhua Yin Yanyan Yang Wenchao Jia Danping Xie Furong Huang Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy Water surface water vis-NIR spectroscopy chemical oxygen demand SMOTE CARS PLS–DA |
| title | Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy |
| title_full | Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy |
| title_fullStr | Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy |
| title_full_unstemmed | Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy |
| title_short | Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy |
| title_sort | discrimination of chemical oxygen demand pollution in surface water based on visible near infrared spectroscopy |
| topic | surface water vis-NIR spectroscopy chemical oxygen demand SMOTE CARS PLS–DA |
| url | https://www.mdpi.com/2073-4441/14/19/3003 |
| work_keys_str_mv | AT xueqinhan discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT xiaoyanchen discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT jinfangma discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT jiazechen discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT baihengxie discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT wenhuayin discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT yanyanyang discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT wenchaojia discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT danpingxie discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy AT furonghuang discriminationofchemicaloxygendemandpollutioninsurfacewaterbasedonvisiblenearinfraredspectroscopy |