Machine learning models with potential application to predict source water quality for treatment purposes: a critical review

References

• Health Canada. Guidance for providing safe drinking water in areas of federal jurisdiction; 2013. Available from: https://www.canada.ca/content/dam/canada/health-canada/migration/healthy-canadians/publications/healthy-living-vie-saine/water-federal-eau/alt/water-federal-eau-eng.pdf.
   Google Scholar
• World Health Organization. Guidelines for drinking-water quality: fourth edition incorporating the first addendum; 2017.
   Google Scholar
• Health Canada. From source to tap the multi-barrier approach to safe drinking water; 2002. Available from: www.ccme.ca.
   Google Scholar
• Boyde CE. Water quality. Cham: Springer; 2016. doi:10.1007/978-3-030-23335-8
   Google Scholar
• Crittenden JC, Trussell RR, Hand DW, et al. MWH’s water treatment – principles and design. 3rd ed.; 2012.
   Google Scholar
• Edzwald JK. Water quality and treatment. A handbook on drinking water. AWWA editor; 6th ed. New York; McGraw Hill; 2011.
   Google Scholar
• Khan AU, Rahman HU, Ali L, et al. Complex linkage between watershed attributes and surface water quality: gaining insight via path analysis. Civil Eng J. 2021;7(4):701–712. doi:10.28991/cej-2021-03091683.
   Google Scholar
• Gullick RW, Grayman WM, Deininger RA. Design of early warning monitoring systems for source waters. J Am Water Works Assoc. 2003;95(11):58–72. Available from: https://www.jstor.org/stable/41311258.
   Web of Science ®Google Scholar
• Jin T, Cai S, Jiang D, et al. A data-driven model for real-time water quality prediction and early warning by an integration method. Environ Sci Pollut Res. 2019;26(29):30374–30385. doi:10.1007/s11356-019-06049-2.
   PubMed Web of Science ®Google Scholar
• Storey MV, Van Der Gaag B, Burns BP. Advances in on-line drinking water quality monitoring and early warning systems. Water Res 2010;45(2):741–747. doi:10.1016/j.watres.2010.08.049.
   PubMed Web of Science ®Google Scholar
• Vélez C, Alfonso L, Sánchez A, et al. Centinela: AN early warning system for the water quality of the Cauca River. J Hydroinf. 2014;16(6):1409–1424. doi:10.2166/hydro.2014.127.
   Web of Science ®Google Scholar
• Delpla I, Rodriguez MJ. Variability of disinfection by-products at a full-scale treatment plant following rainfall events. Chemosphere. 2017;166:453–462. doi:10.1016/j.chemosphere.2016.09.096.
   PubMed Web of Science ®Google Scholar
• Lee CS, Lee YC, Chiang HM. Abrupt state change of river water quality (turbidity): effect of extreme rainfalls and typhoons. Sci Total Environ. 2016;557-558:91–101. doi:10.1016/j.scitotenv.2016.02.213.
   PubMed Web of Science ®Google Scholar
• Canadian Council of Ministers of the Environment. From source to tap: guidance on the multi-barrier approach to safe drinking water; 2004.
   Google Scholar
• Hasan J, Goldbloom-Helzner D, Ichida A, et al. Technologies and techniques for early warning systems to monitor and evaluate drinking water quality: a state-of-the-art review; 2005.
   Google Scholar
• Wang Q, Li S, Jia P, et al. A review of surface water quality models. Sci World J. 2013;2013; doi:10.1155/2013/231768.
   Google Scholar
• Ejigu MT. Overview of water quality modeling. Cogent Eng. 2021;8(1). doi:10.1080/23311916.2021.1891711
   Web of Science ®Google Scholar
• Solomatine DP, Ostfeld A. Data-driven modelling: some past experiences and new approaches. J Hydroinf. 2008;10(1):3–22. doi:10.2166/hydro.2008.015.
   Web of Science ®Google Scholar
• Tsakiris G, Alexakis D. Water quality models : An overview. Eur Water. 2012;37:33–46.
   Google Scholar
• Kim M, Gerba CP, Choi CY. Assessment of physically-based and data-driven models to predict microbial water quality in open channels. J Environ Sci. 2010;22:851–857. doi:10.1016/S1001-0742(09)60188-1.
   Google Scholar
• Chapra SC. Surface water-quality modelling. 2nd ed; Waveland Press; Long Grove, IL; 2008.
   Google Scholar
• Chapra SC. Engineering water quality models and TMDLs. J Water Resour Plann Manage. 2003;129(4):247–256.
   Web of Science ®Google Scholar
• Khadr M, Elshemy M. Data-driven modeling for water quality prediction case study: The drains system associated with Manzala Lake, Egypt. Ain Shams Eng J. 2017;8(4):549–557. doi:10.1016/j.asej.2016.08.004.
   Web of Science ®Google Scholar
• Orouji H, Bozorg Haddad O, Fallah-Mehdipour E, et al. Modeling of water quality parameters using data-driven models. J Environ Eng. 2013;139(7):947–957. doi:10.1061/(ASCE)EE.1943-7870.0000706.
   Web of Science ®Google Scholar
• Rajaee T, Khani S, Ravansalar M. Artificial intelligence-based single and hybrid models for prediction of water quality in rivers: a review. Chemom Intell Lab Syst. 2020;200:103978. doi:10.1016/j.chemolab.2020.103978.
   Web of Science ®Google Scholar
• Tiyasha, Tung TM, Yaseen ZM. A survey on river water quality modelling using artificial intelligence models: 2000–2020. J Hydrol (Amst). 2020;585:124670. doi:10.1016/j.jhydrol.2020.124670.
   Web of Science ®Google Scholar
• Partal T, Kerem H. Estimation and forecasting of daily suspended sediment data using wavelet-neural networks. J Hydrol (Amst). 2008;358(3):317–331. doi:10.1016/j.jhydrol.2008.06.013.
   Web of Science ®Google Scholar
• Rajaee T. Wavelet and neuro-fuzzy conjunction approach for suspended sediment prediction. CLEAN – Soil Air Water. 2010;38(3):275–286. doi:10.1002/clen.200900191.
   Web of Science ®Google Scholar
• Rajaee T, Mirbagheri SA, Zounemat-Kermani M, et al. Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models. Sci Total Environ. 2009;407(17):4916–4927. doi:10.1016/j.scitotenv.2009.05.016.
   PubMed Web of Science ®Google Scholar
• Rajaee T, Mirbagheri SA, Nourani V, et al. Prediction of daily suspended sediment load using wavelet and neuro-fuzzy combined model. Int J Environ Sci Tech. 2010;7(1):93–110.
   Web of Science ®Google Scholar
• Alizadeh MJ, Kavianpour MR. Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. Mar Pollut Bull. 2015;98(1–2):171–178. doi:10.1016/j.marpolbul.2015.06.052.
   PubMed Web of Science ®Google Scholar
• Heddam S. Modelling hourly dissolved oxygen concentration (DO) using dynamic evolving neural-fuzzy inference system (DENFIS)-based approach: Case study of Klamath River at Miller Island Boat Ramp, OR, USA. Environ Sci Pollut Res. 2014;21(15):9212–9227. doi:10.1007/s11356-014-2842-7.
   PubMed Web of Science ®Google Scholar
• Delpla I, Scheili A, Guilherme S, et al. Variations of disinfection by-product levels in small drinking water utilities according to climate change scenarios: a first assessment. J Water Clim Change. 2016;7(1):1–15. doi:10.2166/wcc.2015.102.
   Google Scholar
• Delpla I, Rodriguez MJ. Experimental disinfection by-product formation potential following rainfall events. Water Res 2016;104:340–348. doi:10.1016/j.watres.2016.08.031
   PubMed Web of Science ®Google Scholar
• Banna MH, Imran S, Francisque A, et al. Online drinking water quality monitoring: review on available and emerging technologies. Crit Rev Environ Sci Technol. 2014;44(12):1370–1421. doi:10.1080/10643389.2013.781936.
   Web of Science ®Google Scholar
• Hou D, Song X, Zhang G, et al. An early warning and control system for urban, drinking water quality protection: China’s experience. Environ Sci Pollut Res. 2013;20:4496–4450. doi:10.1007/s11356-012-1406-y.
   PubMed Web of Science ®Google Scholar
• Delpla I, Florea M, Rodriguez MJ. Drinking water source monitoring using early warning systems based on data mining techniques. Water Resour Manage. 2019;33(1):129–140. doi:10.1007/s11269-018-2092-4.
   Web of Science ®Google Scholar
• Dominguez CEA. Protocolo para La Modelación Matemática de Procesos Matematicos. Meteorología Colombiana. 2000;2:33–38.
   Google Scholar
• Refsgaard JC, Henriksen HJ. Modelling guidelines––terminology and guiding principles. Adv Water Resour. 2004;27(1):71–82. doi:10.1016/j.advwatres.2003.08.006.
   Web of Science ®Google Scholar
• Benedini M, Tsakiris G. Water quality modelling for rivers and streams. Dordrecht: Springer; 2013. doi:10.1007/978-94-007-5509-3
   Google Scholar
• Burchard-Levine A, Liu S, Vince F, et al. A hybrid evolutionary data driven model for river water quality early warning. J Environ Manage. 2014;143:8–16. doi:10.1016/j.jenvman.2014.04.017.
   PubMed Web of Science ®Google Scholar
• Michalski RS, Carbonell JG, Mitchell TM. Machine learning: an artificial intelligence approach. M. Kaufmann; 1983; doi:10.1007/978-3-662-12405-5.
   Google Scholar
• Mitchell TM. Machine learning. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. McGraw-Hill; 1997.
   Google Scholar
• Shalev-Shwartz S, Ben-David S. Understanding machine learning: from theory to algorithms. 3rd ed. Cambridge University Press; New York; 2014.
   Google Scholar
• Hastie T, Tibshirani R, Friedman J. The elements of statistical learning data mining, inference, and prediction. 2nd ed.; 2017.
   Google Scholar
• Nilsson NJ. Introduction to machine learning. Mach Learn. 2005;56(2):387–399. Available from: http://www.ncbi.nlm.nih.gov/pubmed/21172442.
   Google Scholar
• James G, Witten D, Hastie T, et al. An introduction to statistical learning – with applications in R. 8th ed.; 2013; doi:10.1007/978-1-4614-7138-7.
   Google Scholar
• Zhang C, Ma YY. Ensemble machine learning. Methods and applications. In: C Zhang, Y Ma, editors. Ensemble machine learning. Springer; 2012. doi:10.1007/978-1-4419-9326-7
   Google Scholar
• Han J, Kamber M, Pei J. Data mining concepts and techniques. 3rd ed. Morgan Kaufmann Publishers; Walthamn, MA; 2014.
   Google Scholar
• Khani S, Rajaee T. Modeling of dissolved oxygen concentration and Its hysteresis behavior in rivers using wavelet transform-based hybrid models. Clean – Soil Air Water. 2017;45(2). doi:10.1002/clen.201500395.
   Web of Science ®Google Scholar
• O’Reilly G, Bezuidenhout CC, Bezuidenhout JJ. Artificial neural networks: applications in the drinking water sector. Water Supply. 2018;18(6):1869–1887. doi:10.2166/ws.2018.016.
   Google Scholar
• Najah A, El-Shafie A, Karim OA, et al. Application of artificial neural networks for water quality prediction. Neural Comput Appl. 2013;22(SUPPL.1):187–201. doi:10.1007/s00521-012-0940-3.
   Google Scholar
• Antanasijević D, Pocajt V, Povrenović D, et al. Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study. Environ Sci Pollut Res. 2013;20(12):9006–9013. doi:10.1007/s11356-013-1876-6.
   PubMed Web of Science ®Google Scholar
• Zadeh LA. Fuzzy sets. Inf Control. 1965;8(3):338–353. doi:10.1016/S0019-9958(65)90241-X.
   Google Scholar
• Jacquin AP, Shamseldin AY. Review of the application of fuzzy inference systems in river flow forecasting. J Hydroinf. 2009;11(3–4):202–210. doi:10.2166/hydro.2009.038.
   Web of Science ®Google Scholar
• Jyh-Shing, Jang R. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern. 1993;23(3):665–685. Available from: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=256541.
   Web of Science ®Google Scholar
• Vapnik VN. The nature of statistical learning theory. IEEE Trans Neural Netw. 1997;8(6):1564–1564. doi:10.1109/tnn.1997.641482.
   PubMedGoogle Scholar
• Singh KP, Basant N, Gupta S. Support vector machines in water quality management. Anal Chim Acta. 2011;703:152–162. doi:10.1016/j.aca.2011.07.027.
   PubMed Web of Science ®Google Scholar
• Nalley D, Adamowski J, Khalil B. Using discrete wavelet transforms to analyze trends in streamflow and precipitation in Quebec and Ontario (1954-2008). J Hydrol. 2012;475:204–228. doi:10.1016/j.jhydrol.2012.09.049.
   Web of Science ®Google Scholar
• Yang XS. Nature-Inspired optimization algorithms. In: Nature-inspired optimization algorithms. Elsevier Inc.; 2014. doi:10.1016/C2013-0-01368-0.
   Google Scholar
• Wang LK, Yang CT. Modern water resources engineering. In: Modern water resources engineering (Humana Pre). Humana Press Inc; 2014. doi:10.1007/978-1-62703-595-8
   Google Scholar
• Merten GH, Capel PD, Minella JPG. Effects of suspended sediment concentration and grain size on three optical turbidity sensors. J Soils Sediments. 2014;14:1235–1124. doi:10.1007/s11368-013-0813-0.
   Web of Science ®Google Scholar
• Liu S, Tai H, Ding Q, et al. A hybrid approach of support vector regression with genetic algorithm optimization for aquaculture water quality prediction. Math Comput Model. 2013;58(3–4):458–465. doi:10.1016/j.mcm.2011.11.021.
   Google Scholar
• Liu S, Che H, Smith K, et al. A method of detecting contamination events using multiple conventional water quality sensors. Environ Monit Assess. 2015;187(1):1–11. doi:10.1007/s10661-014-4189-4.
   PubMed Web of Science ®Google Scholar
• Li L, Jiang P, Xu H, et al. Water quality prediction based on recurrent neural network and improved evidence theory: a case study of Qiantang River, China. Environ Sci Pollut Res. 2019;26(19):19879–19896. doi:10.1007/s11356-019-05116-y.
   PubMed Web of Science ®Google Scholar
• Khalil B, Ouarda TBMJ, St-Hilaire A. Estimation of water quality characteristics at ungauged sites using artificial neural networks and canonical correlation analysis. J Hydrol (Amst). 2011;405(3–4):277–287. doi:10.1016/j.jhydrol.2011.05.024.
   Web of Science ®Google Scholar
• Melesse AM, Ahmad S, Mcclain ME, et al. Suspended sediment load prediction of river systems: An artificial neural network approach. Agric Water Manag. 2011;98:855–866. doi:10.1016/j.agwat.2010.12.012.
   Web of Science ®Google Scholar
• Rajaee T. Wavelet and ANN combination model for prediction of daily suspended sediment load in rivers. Sci Total Environ. 2011;409(15):2917–2928. doi:10.1016/j.scitotenv.2010.11.028.
   PubMed Web of Science ®Google Scholar
• Guo L, Zhao Y, Wang P. Determination of the principal factors of river water quality through cluster analysis method and its prediction. Front Environ Sci Eng. 2012;6(2):238–245. doi:10.1007/s11783-011-0382-7.
   Web of Science ®Google Scholar
• Göransson G, Larson M, Bendz D. Variation in turbidity with precipitation and flow in a regulated river system-river Götä Alv, SW Sweden. Hydrol Earth Syst Sci. 2013;17:2529–2542. doi:10.5194/hess-17-2529-2013.
   Web of Science ®Google Scholar
• Yang TM, Fan SK, Fan C, et al. Establishment of turbidity forecasting model and early-warning system for source water turbidity management using back-propagation artificial neural network algorithm and probability analysis. Environ Monit Assess. 2014;186(8):4925–4934. doi:10.1007/s10661-014-3748-z.
   PubMed Web of Science ®Google Scholar
• Kim SE, Seo IW. Artificial neural network ensemble modeling with conjunctive data clustering for water quality prediction in rivers. J Hydro-Environ Res. 2015;9(3):325–339. doi:10.1016/j.jher.2014.09.006.
   Web of Science ®Google Scholar
• Mälzer HJ, aus der Beek T, Müller S, et al. Comparison of different model approaches for a hygiene early warning system at the lower Ruhr River, Germany. Int J Hyg Environ Health. 2016;219(7):671–680. doi:10.1016/j.ijheh.2015.06.005.
   PubMed Web of Science ®Google Scholar
• Huang M, Tian D, Liu H, et al. A hybrid fuzzy wavelet neural network model with self-adapted fuzzy c-means clustering and genetic algorithm for water quality prediction in rivers. Complexity. 2018;2018; doi:10.1155/2018/8241342.
   Google Scholar
• Rajaee T, Ravansalar M, Adamowski J, et al. A New approach to predict daily pH in rivers based on the “à trous” redundant wavelet transform algorithm. Water Air Soil Pollut. 2018;229(3). doi:10.1007/s11270-018-3715-3.
   Web of Science ®Google Scholar
• Shan W, Cai S, Liu C. A new comprehensive evaluation method for water quality: improved fuzzy support vector machine. Water. 2018;10(10):1303. doi:10.3390/w10101303.
   Web of Science ®Google Scholar
• Shao D, Nong X, Tan X, et al. Daily water quality forecast of the South-To-North Water Diversion Project of China based on the Cuckoo Search-back propagation neural network. Water (Switzerland). 2018;10(10):1471. doi:10.3390/w10101471
   Google Scholar
• Katimon A, Shahid S, Mohsenipour M. Modeling water quality and hydrological variables using ARIMA: a case study of Johor River, Malaysia. Sustainable Water Resour Manage. 2018;4(4):991–998. doi:10.1007/s40899-017-0202-8.
   Web of Science ®Google Scholar
• Rajaee T, Jafari H. Utilization of WGEP and WDT models by wavelet denoising to predict water quality parameters in rivers. J Hydrol Eng. 2018;23(12):04018054. doi:10.1061/(ASCE)HE.1943-5584.0001700.
   Web of Science ®Google Scholar
• Zhu S, Heddam S, Wu S, et al. Extreme learning machine-based prediction of daily water temperature for rivers. Environ Earth Sci. 2019;78(6):202. doi:10.1007/s12665-019-8202-7.
   Web of Science ®Google Scholar
• Peterson KT, Sagan V, Sidike P, et al. Machine learning-based ensemble prediction of water-quality variables using feature-level and decision-level fusion with proximal remote sensing. Photogramm Eng Remote Sens. 2019;85(4):269–280. doi:10.14358/PERS.85.4.269.
   Web of Science ®Google Scholar
• Chen XY, Chau KW. Uncertainty analysis on hybrid double feedforward neural network model for sediment load estimation with LUBE method. Water Resour Manage. 2019;33(10):3563–3577. doi:10.1007/s11269-019-02318-4.
   Web of Science ®Google Scholar
• Boucher M-A, Quilty J, Adamowski J. Data assimilation for streamflow forecasting using extreme learning machines and multilayer perceptrons. Water Resour Res. 2020;56(6). doi:10.1029/2019WR026226
   Web of Science ®Google Scholar
• Heddam S. Simultaneous modelling and forecasting of hourly dissolved oxygen concentration (DO) using radial basis function neural network (RBFNN) based approach: a case study from the Klamath River, Oregon, USA. Model Earth Syst Environ. 2016;2:3. doi:10.1007/s40808-016-0197-4.
   Google Scholar
• Li D, Liu S. Water quality monitoring and management. A. Press editor. Charlotte Cockle; 2019; doi:10.1016/B978-0-12-811330-1.09996-8.
   Google Scholar
• Heddam S. Use of optimally pruned extreme learning machine (OP-ELM) in forecasting dissolved oxygen concentration (DO) several hours in advance: a case study from the Klamath River, Oregon. Environ Processes. 2016;3(4):909–937. doi:10.1007/s40710-016-0172-0.
   Google Scholar
• Nash JE, Sutcliffe JV. River flow forecasting through conceptual models. J Hydrol (Amst). 1970;10:282–290.
   Google Scholar
• Ciaburro G, Iannace G. Machine learning-based algorithms to knowledge extraction from time series data: A review. Data. 2021;6(6):55. doi:10.3390/DATA6060055.
   Web of Science ®Google Scholar
• Zhou Z-H. Machine learning. Springer editor. Tsinghua University Press; 2016. doi:10.1007/978-981-15-1967-3
   Google Scholar
• Alfaro E, Gámez M, García N. Ensemble classification methods with applications in R. In: Alfaro E, Gámez M, García N, editors. Ensemble classification methods with applicationsin R. John Wiley & Sons, Ltd; 2018. doi:10.1002/9781119421566
   Google Scholar
• Ghatak, A. Machine learning with R. Singapore SN editor; 2017. doi:10.1007/978-981-10-6808-9
   Google Scholar