Regression-based machine learning models for nitrate and chloride prediction in surface water in a small agricultural sand plain sub-watershed in southwestern Ontario, Canada DOI Creative Commons

Ahmed Elsayed,

Jana Levison, Andrew Binns

и другие.

Frontiers in Environmental Science, Год журнала: 2025, Номер 13

Опубликована: Март 28, 2025

Machine learning (ML) models have proven to be an efficient technique for better understanding and quantification of surface water quality, especially in agricultural watersheds where considerable anthropogenic activities occur. However, there is a lack systematic investigations that can examine the application different ML regression settings predict quality using group input variables, including hydrological (e.g., flow), meteorological precipitation), field crop cover) conditions. In this study, multiple models, support vector machine (SVM) trees (RT), were employed on 2-year dataset collected from sand plain sub-watershed southwestern Ontario, Canada (i.e., Lower Whitemans Creek) nitrate chloride concentrations at nine sampling sites within sub-watershed. The prediction capabilities these determined evaluation metrics coefficient determination (R 2 ) root-mean squared error (RMSE). general, Gaussian Process Regression (GPR) model was optimal algorithm 0.99 0.98 respectively training testing). According results feature importance analysis, it found conditions (specifically location site (main channel or tributary site) most crucial variables accurate predictions output variables. This study underscores implemented effectively quantify properties easily measurable parameters. These assist decision makers advancing successful actions steps towards protecting available resources.

Язык: Английский

Water quality prediction and classification based on principal component regression and gradient boosting classifier approach DOI Creative Commons

Md. Saikat Islam Khan,

Nazrul Islam, Jia Uddin

и другие.

Journal of King Saud University - Computer and Information Sciences, Год журнала: 2021, Номер 34(8), С. 4773 - 4781

Опубликована: Июнь 14, 2021

Estimating water quality has been one of the significant challenges faced by world in recent decades. This paper presents a prediction model utilizing principal component regression technique. Firstly, index (WQI) is calculated using weighted arithmetic method. Secondly, analysis (PCA) applied to dataset, and most dominant WQI parameters have extracted. Thirdly, predict WQI, different algorithms are used PCA output. Finally, Gradient Boosting Classifier utilized classify status. The proposed system experimentally evaluated on Gulshan Lake-related dataset. results demonstrate 95% accuracy for method 100% classification method, which show credible performance compared with state-of-art models.

Язык: Английский

Процитировано

144
Machine learning algorithms for efficient water quality prediction DOI
Mourade Azrour, Jamal Mabrouki, Ghizlane Fattah

и другие.

Modeling Earth Systems and Environment, Год журнала: 2021, Номер 8(2), С. 2793 - 2801

Опубликована: Авг. 26, 2021

Язык: Английский

Процитировано

120
Advances in machine learning and IoT for water quality monitoring: A comprehensive review DOI Creative Commons
Ismail Essamlali, Hasna Nhaila, Mohamed El Khaïli

и другие.

Heliyon, Год журнала: 2024, Номер 10(6), С. e27920 - e27920

Опубликована: Март 1, 2024

Water holds great significance as a vital resource in our everyday lives, highlighting the important to continuously monitor its quality ensure usability. The advent of the. Internet Things (IoT) has brought about revolutionary shift by enabling real-time data collection from diverse sources, thereby facilitating efficient monitoring water (WQ). By employing Machine learning (ML) techniques, this gathered can be analyzed make accurate predictions regarding quality. These predictive insights play crucial role decision-making processes aimed at safeguarding quality, such identifying areas need immediate attention and implementing preventive measures avert contamination. This paper aims provide comprehensive review current state art monitoring, with specific focus on employment IoT wireless technologies ML techniques. study examines utilization range technologies, including Low-Power Wide Area Networks (LpWAN), Wi-Fi, Zigbee, Radio Frequency Identification (RFID), cellular networks, Bluetooth, context Furthermore, it explores application both supervised unsupervised algorithms for analyzing interpreting collected data. In addition discussing art, survey also addresses challenges open research questions involved integrating (WQM).

Язык: Английский

Процитировано

41
Efficient Data-Driven Machine Learning Models for Water Quality Prediction DOI Creative Commons
Ηλίας Δρίτσας, Μαρία Τρίγκα

Computation, Год журнала: 2023, Номер 11(2), С. 16 - 16

Опубликована: Янв. 18, 2023

Water is a valuable, necessary and unfortunately rare commodity in both developing developed countries all over the world. It undoubtedly most important natural resource on planet constitutes an essential nutrient for human health. Geo-environmental pollution can be caused by many different types of waste, such as municipal solid, industrial, agricultural (e.g., pesticides fertilisers), medical, etc., making water unsuitable use any living being. Therefore, finding efficient methods to automate checking suitability great importance. In context this research work, we leveraged supervised learning approach order design accurate possible predictive models from labelled training dataset identification suitability, either consumption or other uses. We assume set physiochemical microbiological parameters input features that help represent water’s status determine its class (namely safe nonsafe). From methodological perspective, problem treated binary classification task, machine models’ performance (such Naive Bayes–NB, Logistic Regression–LR, k Nearest Neighbours–kNN, tree-based classifiers ensemble techniques) evaluated with without application balancing (i.e., nonuse Synthetic Minority Oversampling Technique–SMOTE), comparing them terms Accuracy, Recall, Precision Area Under Curve (AUC). our demonstration, results show Stacking model after SMOTE 10-fold cross-validation outperforms others Accuracy Recall 98.1%, 100% AUC equal 99.9%. conclusion, article, framework presented support researchers’ efforts toward quality prediction using (ML).

Язык: Английский

Процитировано

39
Large-scale prediction of stream water quality using an interpretable deep learning approach DOI
Hang Zheng,

Yueyi Liu,

Wenhua Wan

и другие.

Journal of Environmental Management, Год журнала: 2023, Номер 331, С. 117309 - 117309

Опубликована: Янв. 17, 2023

Язык: Английский

Процитировано

29
Impacts of watershed and meteorological characteristics on stream water quality resilience DOI
Yujin Park,

Se-Rin Park,

Sang‐Woo Lee

и другие.

Journal of Hydrology, Год журнала: 2025, Номер 652, С. 132663 - 132663

Опубликована: Янв. 7, 2025

Язык: Английский

Процитировано

2
Investigating the critical influencing factors of rural public services resilience in China: A grey relational analysis approach DOI
Hui Yan, Haomiao Li, Lin Zhang

и другие.

Environment Development and Sustainability, Год журнала: 2025, Номер unknown

Опубликована: Янв. 9, 2025

Язык: Английский

Процитировано

1
IoT-Enabled Water Distribution Systems—A Comparative Technological Review DOI Creative Commons

Nibi Kulangara Velayudhan,

Preeja Pradeep, Sethuraman N. Rao

и другие.

IEEE Access, Год журнала: 2022, Номер 10, С. 101042 - 101070

Опубликована: Янв. 1, 2022

Water distribution systems are one of the critical infrastructures and major assets water utility in a nation. The infrastructure consists resources, treatment plants, reservoirs, lines, consumers. A sustainable network management has to take care accessibility, quality, quantity, reliability water. As is becoming depleting resource for coming decades, regulation accounting terms above four parameters task. There have been many efforts towards establishment monitoring controlling framework, capable automating various stages processes. current trending technologies such as Information Communication Technologies (ICT), Internet Things (IoT), Artificial Intelligence (AI) potential track this spatially varying collect, process, analyze attributes events. In work, we investigate role scope IoT different systems. Our survey covers state-of-the-art control networks, status architectures networks. We explore existing systems, providing necessary background information on status. This work also presents an Architecture Intelligent Networks - IoTA4IWNet, real-time believe that build robust network, these components need be designed implemented effectively.

Язык: Английский

Процитировано

38
An improved graph convolutional network with feature and temporal attention for multivariate water quality prediction DOI
Qingjian Ni,

Xuehan Cao,

Chaoqun Tan

и другие.

Environmental Science and Pollution Research, Год журнала: 2022, Номер 30(5), С. 11516 - 11529

Опубликована: Сен. 12, 2022

Язык: Английский

Процитировано

34
Reconstructing Daily Discharge in a Megadelta Using Machine Learning Techniques DOI Creative Commons
Hung Vo Thanh, Đoàn Văn Bình, Sameh A. Kantoush

и другие.

Water Resources Research, Год журнала: 2022, Номер 58(5)

Опубликована: Май 1, 2022

Abstract In this study, six machine learning (ML) models, namely, random forest (RF), Gaussian process regression (GPR), support vector (SVR), decision tree (DT), least squares (LSSVM), and multivariate adaptive spline (MARS) were employed to reconstruct the missing daily‐averaged discharge in a mega‐delta from 1980 2015 using upstream‐downstream multi‐station data. The performance accuracy of each ML model assessed compared with stage‐discharge rating curves (RCs) four statistical indicators, Taylor diagrams, violin plots, scatter time‐series heatmaps. Model input selection was performed mutual information correlation coefficient methods after three data pre‐processing steps: normalization, Fourier series fitting, first‐order differencing. results showed that models are superior their RC counterparts, MARS RF most reliable algorithms, although achieves marginally better than RF. Compared RC, reduced root mean square error (RMSE) by 135% 141% absolute 194% 179%, respectively, year‐round However, developed for climbing (wet season) recession (dry limbs separately worsened slightly Specifically, RMSE falling limb 856 1,040 m 3 /s, while obtained 768 789 respectively. DT is not recommended, GPR SVR provide acceptable results.

Язык: Английский

Процитировано

31