1
|
Gao Z, Chen J, Wang G, Ren S, Fang L, Yinglan A, Wang Q. A novel multivariate time series prediction of crucial water quality parameters with Long Short-Term Memory (LSTM) networks. JOURNAL OF CONTAMINANT HYDROLOGY 2023; 259:104262. [PMID: 37944201 DOI: 10.1016/j.jconhyd.2023.104262] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/06/2023] [Revised: 10/03/2023] [Accepted: 10/27/2023] [Indexed: 11/12/2023]
Abstract
Intelligent prediction of water quality plays a pivotal role in water pollution control, water resource protection, emergency decision-making for sudden water pollution incidents, tracking and evaluation of water quality changes in river basins, and is crucial to ensuring water security. The primary methodology employed in this paper for water quality prediction is as follows: (1) utilizing the comprehensive pollution index method and Mann-Kendall (MK) trend analysis method, an assessment is made of the pollution status and change trend within the basin, while simultaneously extracting the principal water quality parameters based on their respective pollution share rates; (2) employing the spearman method, an analysis is conducted to identify the influential factors impacting each key parameter; (3) subsequently, a water quality parameter prediction model, based on Long Short-Term Memory (LSTM) analysis, is constructed using the aforementioned driving factor analysis outcomes. The developed LSTM model in this study showed good prediction performance. The average coefficient of determination (R2) of the prediction of crucial water quality parameters such as total nitrogen (TN) and dissolved oxygen (DO) reached 0.82 and 0.86 respectively. Additionally, the error analysis of WQI prediction results showed that >75% of the prediction errors were in the range of 0-0.15. The comparative analysis revealed that the LSTM model outperforms both the random forest (RF) model in time series prediction and demonstrates superior robustness and applicability compared to the AutoRegressive Moving Average with eXogenous inputs model (ARMAX). Hence, the model developed in this study offers valuable technical assistance for water quality prediction and early warning systems, particularly in economically disadvantaged regions with limited monitoring capabilities. This contribution facilitates resource optimization and promotes sustainable development.
Collapse
Affiliation(s)
- Zhenyu Gao
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China
| | - Jinyue Chen
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China; Shenzhen Research Institute of Shandong University, Shenzhen 518057, China.
| | - Guoqiang Wang
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China; Innovation Research Center of Satellite Application, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
| | - Shilong Ren
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China
| | - Lei Fang
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China
| | - A Yinglan
- Innovation Research Center of Satellite Application, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
| | - Qiao Wang
- Academician Workstation for Big Data in Ecology and Environment, Environment Research Institute, Shandong University, Qingdao 266237, China
| |
Collapse
|
2
|
Jiang J, Zhao J, Zhao G, Liu L, Song H, Liao S. Recognition, possible source, and risk assessment of organic pollutants in surface water from the Yongding River Basin by non-target and target screening. ENVIRONMENTAL POLLUTION (BARKING, ESSEX : 1987) 2023:121895. [PMID: 37236593 DOI: 10.1016/j.envpol.2023.121895] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Revised: 05/11/2023] [Accepted: 05/23/2023] [Indexed: 05/28/2023]
Abstract
Organic pollutants in aquatic environment could have important implications on pollution stress on aquatic organisms and even on the risk of human exposure. Thus, revealing their occurrence in aquatic environment is essential for water quality monitoring and ecological risk purposes. In this study, a comprehensive two-dimensional gas chromatography connected with time-of-flight mass spectrometry (GC × GC-TOF-MS) was applied, to enable non-target and target analysis of pollutants in the Yongding River Basin. Based on the isotopic patterns, accurate masses and standard substances, certain environmental contaminants were tentatively identified which including polycyclic aromatic hydrocarbon (PAHs), organochlorine pesticides (OCPs), phenols, amines, etc. The compounds with the highest concentration were naphthalene (109.0 ng/L), 2,3-benzofuran (51.5 ng/L) and 1,4-dichlorobenzene (35.9 ng/L) in Guishui River. Wastewater treatment plants (WWTPs) discharges were a main source of pollutants in Yongding River Basin, as the types of compounds screened in the downstream river were relatively similar to those from WWTPs. According to the target analysis, a number of pollutants were selected due to the acute toxicity and cumulative discharge from WWTPs and downstream rivers. Three PAHs (naphthalene, Benzo(b)fluoranthene and pyrene) homologues showed moderate risk to fish and H. Azteca in Yongding River Basin, while the rest of the measured chemicals showed low ecological impact across the entire study area based on the risk assessment. The results are helpful for understanding the necessity of high-throughput screening analysis for assessing water quality of rivers and the discharge emissions of pollutants from WWTPs to the river environment.
Collapse
Affiliation(s)
- Jingqiu Jiang
- Department of Environmental Science & Engineering, North China Electric Power University, Baoding, 071000, China; Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, No.12 South Zhongguancun Ave., Haidian District, Beijing, 100081, China
| | - Jian Zhao
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing, 100012, China
| | - Gaofeng Zhao
- Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, No.12 South Zhongguancun Ave., Haidian District, Beijing, 100081, China.
| | - Lin Liu
- Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, No.12 South Zhongguancun Ave., Haidian District, Beijing, 100081, China
| | - Huarong Song
- Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, No.12 South Zhongguancun Ave., Haidian District, Beijing, 100081, China; Qingdao Engineering Research Center for Rural Environment, College of Resources and Environment, Qingdao Agricultural University, Qingdao, 266109, China
| | - Siyuan Liao
- Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, No.12 South Zhongguancun Ave., Haidian District, Beijing, 100081, China
| |
Collapse
|