Assessing and predicting water quality index with key water parameters by machine learning models in coastal cities, China DOI Creative Commons

Jing Xu,

Yuming Mo,

Senlin Zhu

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(13), P. e33695 - e33695

Published: June 28, 2024

The water quality index (WQI) is a widely used tool for comprehensive assessment of river environments. However, its calculation involves numerous parameters, making sample collection and laboratory analysis time-consuming costly. This study aimed to identify key parameters the most reliable prediction models that could provide maximum accuracy using minimal indicators. Water from 2020 2023 were collected including nine biophysical chemical indicators in seventeen rivers Yancheng Nantong, two coastal cities Jiangsu Province, China, adjacent Yellow Sea. Linear regression seven machine learning (Artificial Neural Network (ANN), Self-Organizing Maps (SOM), K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF), Extreme Gradient Boosting (XGB) Stochastic (SGB)) developed predict WQI different groups input variables based on correlation analysis. results indicated improved 2022 but deteriorated 2023, with inland stations exhibiting better conditions than ones, particularly terms turbidity nutrients. environment was comparatively Nantong Yancheng, mean values approximately 55.3–72.0 56.4–67.3, respectively. classifications "Good" "Medium" accounted 80 % records, no instances "Excellent" 2 classified as "Bad". performance all models, except SOM, addition variables, achieving R2 higher 0.99 such SVM, RF, XGB, SGB. RF XGB total phosphorus (TP), ammonia nitrogen (AN), dissolved oxygen (DO) (R2 = 0.98 0.91 training testing phase) predicting values, TP AN (accuracy 85 %) grades. "Low" grades highest at 90 %, followed by level 70 %. model contribute efficient evaluation identifying facilitating effective management basins.

Language: Английский

Improved method for benthic ecosystem health assessment by integrating chemical indexes into multiple biological indicator species—A case study of the Baiyangdian Lake, China DOI

Xianjing Liu,

Ying Wang,

Xiangyu Meng

et al.

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 335, P. 117530 - 117530

Published: Feb. 28, 2023

Language: Английский

Citations

16
A survey on applications of machine learning algorithms in water quality assessment and water supply and management DOI Creative Commons
Abdulhalık Oğuz, Ömer Faruk Ertuğrul

Water Science & Technology Water Supply, Journal Year: 2023, Volume and Issue: 23(2), P. 895 - 922

Published: Feb. 1, 2023

Abstract Managing water resources and determining the quality of surface groundwater is one most significant issues fundamental to human societal well-being. The process maintaining managing well involves complications due human-induced errors. Therefore, applications that facilitate enhance these processes have gained importance. In recent years, machine learning techniques been applied successfully in preservation management planning resources. Water researchers effectively used integrate them into public systems. this study, data sources, pre-processing, methods research are briefly mentioned, algorithms categorized. Then, a general summary literature presented on determination management. Lastly, study was detailed using investigations two publicly shared datasets.

Language: Английский

Citations

15
Global water quality indices: Development, implications, and limitations DOI Creative Commons
Dheeraj Kumar, Rakesh Kumar, Madhuben Sharma

et al.

Total Environment Advances, Journal Year: 2023, Volume and Issue: 9, P. 200095 - 200095

Published: Dec. 30, 2023

Water quality index is crucial for improving water and clean supply to achieve sustainable development goals directly related water, agriculture, biodiversity, health, climate actions. examines the vital relationship between demand, focusing on role that (WQ) plays in integrated environmental management. This study evaluates methodology limitations of several studies by doing a thorough examination regional global WQ indices synthesizing results. Quality Indices (WQIs) have been used measure since 1960s, offering mechanism changes at specific needs challenges. review assesses using indexes based aims provide detailed analysis various WQIs utilized across globe. The stated measurements into single number, which are categorized as poor, marginal, fair, excellent, exceptional, depict clearly understandably WQ. However, region-specific required due variety standards established national international organizations, well different pollution prevention elements. Thus, there continual interest developing exact suitable region or geographic area. Still, structured in-depth literature examine current research, evaluate, highlight drawbacks methodologies employed each phase. offers insightful information researchers, decision-makers, practitioners tackling ever-changing problems resource debate concentrates WQI-related topics, such how evolved, what variables define their parameter requirements, restrictions have, widely used, benefits over one another regarding worldwide applicability.

Language: Английский

Citations

15
Assessing water quality in North-East Algeria: a comprehensive study using water quality index (WQI) and PCA DOI Creative Commons

Fatma Zohra Guenouche,

Amina Mesbahi-Salhi,

Rachid Zegait

et al.

Water Practice & Technology, Journal Year: 2024, Volume and Issue: unknown

Published: March 27, 2024

Abstract Ensuring high water quality in Algeria, particularly Annaba, is crucial for the well-being of its population and sustainable development diverse ecosystems. The study focuses on Cheffia Dam, Oued El Aneb, Treat boreholes as sources drinking water. index (WQI) used to assess based various physico-chemical parameters. research spans from January December 2021, analyzing 16 parameters, such temperature, pH, conductivity, turbidity, total hardness, calcium, magnesium, sodium, potassium, chloride, nitrate, sulfate, phosphate, iron, this results a 36 samples 576 analyses. Principal component analysis (PCA) employed delve into interrelationships between variables, revealing distinct characteristics each site. This study, first kind, provides comprehensive 1-year evaluation Annaba. collected data serve valuable resource future management decisions, highlighting both temporal spatial variations. current indicates that adherence standards, application WQI reveal are generally good throughout year with excellent autumn. However, challenges elevated turbidity dam necessitate targeted interventions.

Language: Английский

Citations

5
Assessing and predicting water quality index with key water parameters by machine learning models in coastal cities, China DOI Creative Commons

Jing Xu,

Yuming Mo,

Senlin Zhu

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(13), P. e33695 - e33695

Published: June 28, 2024

The water quality index (WQI) is a widely used tool for comprehensive assessment of river environments. However, its calculation involves numerous parameters, making sample collection and laboratory analysis time-consuming costly. This study aimed to identify key parameters the most reliable prediction models that could provide maximum accuracy using minimal indicators. Water from 2020 2023 were collected including nine biophysical chemical indicators in seventeen rivers Yancheng Nantong, two coastal cities Jiangsu Province, China, adjacent Yellow Sea. Linear regression seven machine learning (Artificial Neural Network (ANN), Self-Organizing Maps (SOM), K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF), Extreme Gradient Boosting (XGB) Stochastic (SGB)) developed predict WQI different groups input variables based on correlation analysis. results indicated improved 2022 but deteriorated 2023, with inland stations exhibiting better conditions than ones, particularly terms turbidity nutrients. environment was comparatively Nantong Yancheng, mean values approximately 55.3–72.0 56.4–67.3, respectively. classifications "Good" "Medium" accounted 80 % records, no instances "Excellent" 2 classified as "Bad". performance all models, except SOM, addition variables, achieving R2 higher 0.99 such SVM, RF, XGB, SGB. RF XGB total phosphorus (TP), ammonia nitrogen (AN), dissolved oxygen (DO) (R2 = 0.98 0.91 training testing phase) predicting values, TP AN (accuracy 85 %) grades. "Low" grades highest at 90 %, followed by level 70 %. model contribute efficient evaluation identifying facilitating effective management basins.

Language: Английский

Citations

5