{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T01:49:11Z","timestamp":1777081751399,"version":"3.51.4"},"reference-count":53,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T00:00:00Z","timestamp":1753228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CIC-UMSNH","award":["8762877"],"award-info":[{"award-number":["8762877"]}]},{"name":"CIC-UMSNH","award":["18371"],"award-info":[{"award-number":["18371"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Given the importance of turbidity as a key indicator of water quality, this study investigates the use of a convolutional neural network (CNN) to classify water samples into five turbidity-based categories. These classes were defined using ranges inspired by Mexican environmental regulations and generated from 33 laboratory-prepared mixtures with varying concentrations of suspended clay particles. Red, green, and blue (RGB) images of each sample were captured under controlled optical conditions, and turbidity was measured using a calibrated turbidimeter. A transfer learning (TL) approach was applied using EfficientNet-B0, a deep yet computationally efficient CNN architecture. The model achieved an average accuracy of 99% across ten independent training runs, with minimal misclassifications. The use of a lightweight deep learning model, combined with a standardized image acquisition protocol, represents a novel and scalable alternative for rapid, low-cost water quality assessment in future environmental monitoring systems.<\/jats:p>","DOI":"10.3390\/computation13080178","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T16:04:51Z","timestamp":1753286691000},"page":"178","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Image-Based Water Turbidity Classification Scheme Using a Convolutional Neural Network"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1292-5537","authenticated-orcid":false,"given":"Itzel Luviano","family":"Soto","sequence":"first","affiliation":[{"name":"Facultad de Ingenier\u00eda Civil, Universidad Michoacana de San Nicol\u00e1s de Hidalgo, Edificio C, Ciudad Universitaria, Francisco J. M\u00fajica S\/N, Col. Fel\u00edcitas del R\u00edo, Morelia C.P. 58030, Michoac\u00e1n, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-527X","authenticated-orcid":false,"given":"Yajaira","family":"Concha-S\u00e1nchez","sequence":"additional","affiliation":[{"name":"Facultad de Ingenier\u00eda Civil, Universidad Michoacana de San Nicol\u00e1s de Hidalgo, Edificio C, Ciudad Universitaria, Francisco J. M\u00fajica S\/N, Col. Fel\u00edcitas del R\u00edo, Morelia C.P. 58030, Michoac\u00e1n, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5394-8634","authenticated-orcid":false,"given":"Alfredo","family":"Raya","sequence":"additional","affiliation":[{"name":"Facultad de Ingenier\u00eda El\u00e9ctrica, Universidad Michoacana de San Nicol\u00e1s de Hidalgo, Ciudad Universitaria, Francisco J. M\u00fajica S\/N, Col. Fel\u00edcitas del R\u00edo, Morelia C.P. 58040, Michoac\u00e1n, Mexico"},{"name":"Centro de Ciencias Exactas, Universidad del B\u00edo-B\u00edo, Casilla 447, Chill\u00e1n 378000, Chile"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"ref_1","unstructured":"National Water Commission (CONAGUA) (2025, April 08). Laboratories of the National Water Commission, Available online: https:\/\/laboratorios.conagua.gob.mx:8446\/LABORATORIOS\/Pages\/Laboratorios.aspx."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"121171","DOI":"10.1016\/j.physa.2019.121171","article-title":"Assessment of physical and chemical indicators on water turbidity","volume":"527","author":"Miljojkovic","year":"2019","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1002\/lom3.10120","article-title":"Black disk visibility, turbidity, and total suspended solids in rivers: A comparative evaluation","volume":"14","author":"West","year":"2016","journal-title":"Limnol. Oceanogr. Methods"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1016\/j.scitotenv.2017.12.173","article-title":"Turbidity composition and the relationship with microbial attachment and UV inactivation efficacy","volume":"624","author":"Farrell","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_5","unstructured":"Dunlop, J., McGregor, G., and Horrigan, N. (2005). Potential impacts of salinity and turbidity in riverine ecosystems, National Action Plan for Salinity and Water Quality, State of Queensland."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1577\/1548-8659(1987)7<34:TAAWQS>2.0.CO;2","article-title":"Turbidity as a water quality standard for salmonid habitats in Alaska","volume":"7","author":"Lloyd","year":"1987","journal-title":"N. Am. J. Fish. Manag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"273","DOI":"10.3390\/w2020273","article-title":"Turbidity as an indicator of water quality in diverse watersheds of the upper Pecos River basin","volume":"2","author":"Huey","year":"2010","journal-title":"Water"},{"key":"ref_8","unstructured":"Packman, J.J., Comings, K.J., and Booth, D.B. (1999). Using turbidity to determine total suspended solids in urbanizing streams in the Puget Lowlands. Confronting Uncertainty: Managing Change in Water Resources and the Environment, Canadian Water Resources Association Annual Meeting, Vancouver, BC, Canada, 27\u201329 October 1999, Canadian Water Resources Association. Available online: http:\/\/hdl.handle.net\/1773\/16333."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/hyp.3360090108","article-title":"Potential of turbidity monitoring for measuring the transport of suspended solids in streams","volume":"9","author":"Gippel","year":"1995","journal-title":"Hydrol. Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1006\/jema.1996.0051","article-title":"The potential of field turbidity measurements for the computation of total phosphorus and suspended solids loads","volume":"47","author":"Grayson","year":"1996","journal-title":"J. Environ. Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"8311","DOI":"10.3390\/s91008311","article-title":"Turbidimeter design and analysis: A review on optical fiber sensors for the measurement of water turbidity","volume":"9","author":"Omar","year":"2009","journal-title":"Sensors"},{"key":"ref_12","unstructured":"Secretar\u00eda de Econom\u00eda (2001). NMX-AA-038-SCFI-2001: Water Analysis\u2014Determination of Turbidity in Natural, Wastewater, and Treated Wastewater\u2014Test Method, Cancels NMX-AA-038-1981. CDU: 543.31\/.38."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"118973","DOI":"10.1016\/j.watres.2022.118973","article-title":"The role of deep learning in urban water management: A critical review","volume":"223","author":"Fu","year":"2022","journal-title":"Water Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.15244\/pjoes\/103470","article-title":"Developing a sediment rating curve model using the curve slope","volume":"29","author":"Salarijazi","year":"2020","journal-title":"Pol. J. Environ. Stud."},{"key":"ref_15","unstructured":"Standiford, R.B. (2001, January 22\u201325). Turbidity and total suspended solid concentration dynamics in streamflow from California oak woodland watersheds. Proceedings of the Fifth Symposium on Oak Woodlands: Oaks in California\u2019s Challenging Landscape, San Diego, CA, USA. Gen. Tech. Rep. PSW-GTR-184."},{"key":"ref_16","first-page":"78","article-title":"Evaluation the correlation between turbidity and total suspended solids with other chemical parameters in Yazd wastewater treatment effluent plant","volume":"1","author":"Nikoonahad","year":"2016","journal-title":"J. Environ. Health Sustain. Dev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1080\/07438140409354355","article-title":"Use of Transparency Tubes for Rapid Assessment of Total Suspended Solids and Turbidity in Streams","volume":"20","author":"Anderson","year":"2004","journal-title":"Lake Reserv. Manag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1007\/s10661-019-7775-7","article-title":"Determining suspended solids and total phosphorus from turbidity: Comparison of high-frequency sampling with conventional monitoring methods","volume":"191","author":"Villa","year":"2019","journal-title":"Environ. Monit. Assess."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2445","DOI":"10.2166\/wst.2011.779","article-title":"Relationship between turbidity and total suspended solids concentration within a combined sewer system","volume":"64","author":"Hannouche","year":"2011","journal-title":"Water Sci. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e18254","DOI":"10.7717\/peerj.18254","article-title":"Turbidivision: A computer vision application for estimating turbidity from underwater images","volume":"12","author":"Rudy","year":"2024","journal-title":"PeerJ"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lopez-Betancur, D., Moreno, I., Guerrero-Mendez, C., Saucedo-Anaya, T., Gonz\u00e1lez, E., Bautista-Capetillo, C., and Gonz\u00e1lez-Trinidad, J. (2022). Convolutional neural network for measurement of suspended solids and turbidity. Appl. Sci., 12.","DOI":"10.3390\/app12126079"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.2166\/wst.2018.030","article-title":"A novel image processing-based system for turbidity measurement in domestic and industrial wastewater","volume":"77","author":"Mullins","year":"2018","journal-title":"Water Sci. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"161","DOI":"10.25103\/jestr.144.20","article-title":"Analysis of artificial vision techniques for implementation of virtual instrumentation system to measure water turbidity","volume":"14","author":"Guapacho","year":"2021","journal-title":"J. Eng. Sci. Technol. Rev."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Parra, L., Ahmad, A., Sendra, S., Lloret, J., and Lorenz, P. (2024). Combination of machine learning and RGB sensors to quantify and classify water turbidity. Chemosensors, 12.","DOI":"10.3390\/chemosensors12030034"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"83589","DOI":"10.1109\/ACCESS.2019.2924462","article-title":"Using a digital camera combined with fitting algorithm and T-S fuzzy neural network to determine the turbidity in water","volume":"7","author":"Cao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s13762-022-04531-y","article-title":"An image-based deep learning model for water turbidity estimation in laboratory conditions","volume":"20","author":"Feizi","year":"2023","journal-title":"Int. J. Environ. Sci. Technol."},{"key":"ref_27","first-page":"100951","article-title":"Application of machine learning techniques to derive sea water turbidity from Sentinel-2 imagery","volume":"30","author":"Ottaviani","year":"2023","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"117406","DOI":"10.1016\/j.watres.2021.117406","article-title":"A novel framework to predict water turbidity using Bayesian modeling","volume":"202","author":"Huang","year":"2021","journal-title":"Water Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"112657","DOI":"10.1016\/j.jenvman.2021.112657","article-title":"Turbidity prediction of lake-type raw water using random forest model based on meteorological data: A case study of Tai lake, China","volume":"290","author":"Zhang","year":"2021","journal-title":"J. Environ. Manag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"109210","DOI":"10.1016\/j.ecolmodel.2020.109210","article-title":"Study on turbidity prediction method of reservoirs based on long short term memory neural network","volume":"432","author":"Song","year":"2020","journal-title":"Ecol. Model."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"535","DOI":"10.29207\/resti.v8i4.5875","article-title":"Deep learning-based waste classification with transfer learning using EfficientNet-B0 model","volume":"8","author":"Risfendra","year":"2024","journal-title":"J. Resti (Rekayasa Sist. Dan Teknol. Inf.)"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"214","DOI":"10.2166\/wqrj.2024.061","article-title":"Water quality polluted by total suspended solids classified within an artificial neural network approach","volume":"60","author":"Raya","year":"2025","journal-title":"Water Qual. Res. J."},{"key":"ref_33","unstructured":"SEMARNAT (Secretariat of Environment and Natural Resources) (2025, March 25). Water Quality Indicators. Government of Mexico, Available online: https:\/\/apps1.semarnat.gob.mx:8443\/dgeia\/compendio_2020\/dgeiawf.semarnat.gob.mx_8080\/approot\/dgeia_mce\/html\/RECUADROS_INT_GLOS\/D3_AGUA\/D3_AGUA04\/D3_R_AGUA05_01.htm."},{"key":"ref_34","unstructured":"Perry, C., and Taylor, K. (2009). Environmental Sedimentology, John Wiley & Sons, Blackwell Publishing."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Nayak, D.R., Padhy, N., Mallick, P.K., Zymbler, M., and Kumar, S. (2022). Brain tumor classification using dense efficient-net. Axioms, 11.","DOI":"10.3390\/axioms11010034"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shahriar Maswood, M.M., Hussain, T., Khan, M.B., Islam, M.T., and Alharbi, A.G. (2020, January 4\u20137). CNN based detection of the severity of diabetic retinopathy from the fundus photography using EfficientNet-B5. Proceedings of the 2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), Virtual.","DOI":"10.1109\/IEMCON51383.2020.9284944"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"U\u00c7an, M., Kaya, B., and Kaya, M. (2022, January 25\u201326). Multi-class gastrointestinal images classification using EfficientNet-B0 CNN model. Proceedings of the 2022 International Conference on Data Analytics for Business and Industry (ICDABI), Sakhir, Bahrain.","DOI":"10.1109\/ICDABI56818.2022.10041447"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"14078","DOI":"10.1109\/ACCESS.2021.3051085","article-title":"Classification of remote sensing images using EfficientNet-B3 CNN model with attention","volume":"9","author":"Alhichri","year":"2021","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhang, X.W., Sun, Z., Zheng, Y.L., Su, S.C., and Chen, F.J. (2022). Identification of oil tea (Camellia oleifera C.Abel) cultivars using EfficientNet-B4 CNN model with attention mechanism. Forests, 13.","DOI":"10.3390\/f13010001"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"134065","DOI":"10.1109\/ACCESS.2021.3113337","article-title":"EfficientNet-Lite and hybrid CNN-KNN implementation for facial expression recognition on Raspberry Pi","volume":"9","author":"Nazir","year":"2021","journal-title":"IEEE Access"},{"key":"ref_41","unstructured":"Luviano-Soto, I., Concha-S\u00e1nchez, Y., Raya, A., and Flores-Fern\u00e1ndez, G.C. (2025). Comparative Study of Convolutional Neural Networks for Evaluating Suspended Solids Pollution Levels in Water, Internal Report."},{"key":"ref_42","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA. Available online: https:\/\/proceedings.mlr.press\/v97\/tan19a.html."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_44","unstructured":"Yu, T., and Zhu, H. (2020). Hyper-parameter optimization: A review of algorithms and applications. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Seliya, N., Khoshgoftaar, T.M., and Van Hulse, J. (2009, January 2\u20134). A study on the relationships of classifier performance metrics. Proceedings of the 2009 21st IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Newark, NJ, USA.","DOI":"10.1109\/ICTAI.2009.25"},{"key":"ref_46","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_47","unstructured":"Romano, F. (2015). Learning Python: Learn to Code like a Professional with Python\u2014An Open Source, Versatile, and Powerful Programming Language, Packt Publishing Ltd."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3503","DOI":"10.1007\/s13369-023-08064-5","article-title":"A combined computer vision and convolution neural network approach to classify turbid water samples in accordance with national water quality standards","volume":"49","author":"Zainuddin","year":"2024","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.2166\/aqua.2024.085","article-title":"Estimating drinking water turbidity using images collected by a smartphone camera","volume":"73","author":"Jantarakasem","year":"2024","journal-title":"AQUA Water Infrastruct. Ecosyst. Soc."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Nie, Y., Chen, Y., Guo, J., Li, S., Xiao, Y., Gong, W., and Lan, R. (2025). An improved CNN model in image classification application on water turbidity. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-93521-4"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Trejo-Z\u00fa\u00f1iga, I., Moreno, M., Santana-Cruz, R.F., and Mel\u00e9ndez-V\u00e1zquez, F. (2024). Deep-learning-driven turbidity level classification. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8080089"},{"key":"ref_52","first-page":"102260","article-title":"Prediction of water turbidity in a marine environment using machine learning: A case study of Hong Kong","volume":"52","author":"Kumar","year":"2022","journal-title":"Reg. Stud. Mar. Sci."},{"key":"ref_53","first-page":"101139","article-title":"Machine learning approach to predict the turbidity of Saki Lake, Telangana, India, using remote sensing data","volume":"29","author":"Mamatha","year":"2024","journal-title":"Meas. Sens."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/13\/8\/178\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:14:57Z","timestamp":1760033697000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/13\/8\/178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,23]]},"references-count":53,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["computation13080178"],"URL":"https:\/\/doi.org\/10.3390\/computation13080178","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,23]]}}}