Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant

Autores
Gauto, Víctor Hugo; Utgés, Enid Marta; Hervot, Elsa Ivonne; Tenev, María Daniela; Farías, Alejandro Rubén
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Clean water is a scarce resource, fundamental for human development and well-being. Remote sensing techniques are used to monitor and retrieve quality estimators from water bodies. In situ sampling is an essential and labour-intensive task with high costs. As an alternative, a large water quality dataset from a potabilisation plant can be beneficial to this step. Combining laboratory measurements from a water treatment plant in North-East Argentina and spectral data from the Sentinel-2 satellite platform, several regression algorithms were proposed, trained, and compared for turbidity estimation at the plant inlet water in a local river. The highest performance metrics were from a Random Forest model with a coefficient of determination close to 1 (0.913) and the lowest root-mean-squared error (143.9 nephelometric turbidity units). Global feature importance and partial dependencies profile techniques identified the most influential spectral bands. Maps and histograms were made to explore the spatial distribution of turbidity.
Fil: Gauto, Víctor Hugo. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Utgés, Enid Marta. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Hervot, Elsa Ivonne. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Tenev, María Daniela. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Farías, Alejandro Rubén. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Materia
random forest
remote sensing
Sentinel-2
turbidity
water quality
turbidez
calidad del agua
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Attribution-NonCommercial-ShareAlike 4.0 International
Repositorio
Repositorio Institucional Abierto (UTN)
Institución
Universidad Tecnológica Nacional
OAI Identificador
oai:ria.utn.edu.ar:20.500.12272/13416
Acceder
id RIAUTN_87e23d4e86e4f2a8081995f6260c2e30
oai_identifier_str oai:ria.utn.edu.ar:20.500.12272/13416
network_acronym_str RIAUTN
repository_id_str a
network_name_str Repositorio Institucional Abierto (UTN)
spelling Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plantGauto, Víctor HugoUtgés, Enid MartaHervot, Elsa IvonneTenev, María DanielaFarías, Alejandro Rubénrandom forestremote sensingSentinel-2turbiditywater qualityturbidezcalidad del aguaClean water is a scarce resource, fundamental for human development and well-being. Remote sensing techniques are used to monitor and retrieve quality estimators from water bodies. In situ sampling is an essential and labour-intensive task with high costs. As an alternative, a large water quality dataset from a potabilisation plant can be beneficial to this step. Combining laboratory measurements from a water treatment plant in North-East Argentina and spectral data from the Sentinel-2 satellite platform, several regression algorithms were proposed, trained, and compared for turbidity estimation at the plant inlet water in a local river. The highest performance metrics were from a Random Forest model with a coefficient of determination close to 1 (0.913) and the lowest root-mean-squared error (143.9 nephelometric turbidity units). Global feature importance and partial dependencies profile techniques identified the most influential spectral bands. Maps and histograms were made to explore the spatial distribution of turbidity.Fil: Gauto, Víctor Hugo. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.Fil: Utgés, Enid Marta. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.Fil: Hervot, Elsa Ivonne. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.Fil: Tenev, María Daniela. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.Fil: Farías, Alejandro Rubén. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.International Centre for Sustainable Development of Energy, Water and Environment Systems (SDEWES)2025-07-01T20:22:08Z2025-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articulopdfapplication/pdfGauto, V., Utges, E., Hervot, E., Tenev, M. D., & Farías, A. (2025). Turbidity Estimation by Machine Learning Modelling and Remote Sensing Techniques Applied to a Water Treatment Plant. Journal of Sustainable Development of Energy, Water and Environment Systems, 13(2), 1-17.https://hdl.handle.net/20.500.12272/13416https://doi.org/10.13044/j.sdewes.d13.0539engCaracterización fisicoquímica de cuerpos de aguas continentales para la evaluación de la utilización de algoritmos en el monitoreo satelital de la calidad del aguaMSPPBRE0008091MSECRE0008604Estimar indicadores de calidad de agua en la cuenca media del río Paraná para el desarrollo de un algoritmo mediante técnicas de teledetección satelitalinfo:eu-repo/semantics/openAccessAttribution-NonCommercial-ShareAlike 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-sa/4.0/Acceso abiertoreponame:Repositorio Institucional Abierto (UTN)instname:Universidad Tecnológica Nacional2026-09-24T12:48:13Zoai:ria.utn.edu.ar:20.500.12272/13416instacron:UTNInstitucionalhttp://ria.utn.edu.ar/Universidad públicaNo correspondehttp://ria.utn.edu.ar/oaigestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:a2026-09-24 12:48:14.731Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacionalfalse
dc.title.none.fl_str_mv Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
title Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
spellingShingle Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
Gauto, Víctor Hugo
random forest
remote sensing
Sentinel-2
turbidity
water quality
turbidez
calidad del agua
title_short Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
title_full Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
title_fullStr Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
title_full_unstemmed Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
title_sort Turbidity estimation by machine learning modelling and remote sensing techniques applied to a water treatment plant
dc.creator.none.fl_str_mv Gauto, Víctor Hugo
Utgés, Enid Marta
Hervot, Elsa Ivonne
Tenev, María Daniela
Farías, Alejandro Rubén
author Gauto, Víctor Hugo
author_facet Gauto, Víctor Hugo
Utgés, Enid Marta
Hervot, Elsa Ivonne
Tenev, María Daniela
Farías, Alejandro Rubén
author_role author
author2 Utgés, Enid Marta
Hervot, Elsa Ivonne
Tenev, María Daniela
Farías, Alejandro Rubén
author2_role author
author
author
author
dc.subject.none.fl_str_mv random forest
remote sensing
Sentinel-2
turbidity
water quality
turbidez
calidad del agua
topic random forest
remote sensing
Sentinel-2
turbidity
water quality
turbidez
calidad del agua
dc.description.none.fl_txt_mv Clean water is a scarce resource, fundamental for human development and well-being. Remote sensing techniques are used to monitor and retrieve quality estimators from water bodies. In situ sampling is an essential and labour-intensive task with high costs. As an alternative, a large water quality dataset from a potabilisation plant can be beneficial to this step. Combining laboratory measurements from a water treatment plant in North-East Argentina and spectral data from the Sentinel-2 satellite platform, several regression algorithms were proposed, trained, and compared for turbidity estimation at the plant inlet water in a local river. The highest performance metrics were from a Random Forest model with a coefficient of determination close to 1 (0.913) and the lowest root-mean-squared error (143.9 nephelometric turbidity units). Global feature importance and partial dependencies profile techniques identified the most influential spectral bands. Maps and histograms were made to explore the spatial distribution of turbidity.
Fil: Gauto, Víctor Hugo. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Utgés, Enid Marta. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Hervot, Elsa Ivonne. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Tenev, María Daniela. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
Fil: Farías, Alejandro Rubén. Universidad Tecnológica Nacional. Facultad Regional Resistencia. Grupo de Investigación Sobre Temas Ambientales y Químicos; Argentina.
description Clean water is a scarce resource, fundamental for human development and well-being. Remote sensing techniques are used to monitor and retrieve quality estimators from water bodies. In situ sampling is an essential and labour-intensive task with high costs. As an alternative, a large water quality dataset from a potabilisation plant can be beneficial to this step. Combining laboratory measurements from a water treatment plant in North-East Argentina and spectral data from the Sentinel-2 satellite platform, several regression algorithms were proposed, trained, and compared for turbidity estimation at the plant inlet water in a local river. The highest performance metrics were from a Random Forest model with a coefficient of determination close to 1 (0.913) and the lowest root-mean-squared error (143.9 nephelometric turbidity units). Global feature importance and partial dependencies profile techniques identified the most influential spectral bands. Maps and histograms were made to explore the spatial distribution of turbidity.
publishDate 2025
dc.date.none.fl_str_mv 2025-07-01T20:22:08Z
2025-06-01
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv Gauto, V., Utges, E., Hervot, E., Tenev, M. D., & Farías, A. (2025). Turbidity Estimation by Machine Learning Modelling and Remote Sensing Techniques Applied to a Water Treatment Plant. Journal of Sustainable Development of Energy, Water and Environment Systems, 13(2), 1-17.
https://hdl.handle.net/20.500.12272/13416
https://doi.org/10.13044/j.sdewes.d13.0539
identifier_str_mv Gauto, V., Utges, E., Hervot, E., Tenev, M. D., & Farías, A. (2025). Turbidity Estimation by Machine Learning Modelling and Remote Sensing Techniques Applied to a Water Treatment Plant. Journal of Sustainable Development of Energy, Water and Environment Systems, 13(2), 1-17.
url https://hdl.handle.net/20.500.12272/13416
https://doi.org/10.13044/j.sdewes.d13.0539
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Caracterización fisicoquímica de cuerpos de aguas continentales para la evaluación de la utilización de algoritmos en el monitoreo satelital de la calidad del agua
MSPPBRE0008091
MSECRE0008604
Estimar indicadores de calidad de agua en la cuenca media del río Paraná para el desarrollo de un algoritmo mediante técnicas de teledetección satelital
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
Attribution-NonCommercial-ShareAlike 4.0 International
http://creativecommons.org/licenses/by-nc-sa/4.0/
Acceso abierto
eu_rights_str_mv openAccess
rights_invalid_str_mv Attribution-NonCommercial-ShareAlike 4.0 International
http://creativecommons.org/licenses/by-nc-sa/4.0/
Acceso abierto
dc.format.none.fl_str_mv pdf
application/pdf
dc.publisher.none.fl_str_mv International Centre for Sustainable Development of Energy, Water and Environment Systems (SDEWES)
publisher.none.fl_str_mv International Centre for Sustainable Development of Energy, Water and Environment Systems (SDEWES)
dc.source.none.fl_str_mv reponame:Repositorio Institucional Abierto (UTN)
instname:Universidad Tecnológica Nacional
reponame_str Repositorio Institucional Abierto (UTN)
collection Repositorio Institucional Abierto (UTN)
instname_str Universidad Tecnológica Nacional
repository.name.fl_str_mv Repositorio Institucional Abierto (UTN) - Universidad Tecnológica Nacional
repository.mail.fl_str_mv gestionria@rec.utn.edu.ar; fsuarez@rec.utn.edu.ar
_version_ 1877230954995515392
score 13.24418

Publicaciones similares