Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks

Abstract Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Michael De Santi, Usman T. Khan, Matthew Arnold, Jean-François Fesselet, Syed Imran Ali
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Water supply for domestic and industrial purposes TD201-500
Acceso en línea:	https://doaj.org/article/e9da9bf2a52a4a6da9fd0d364b822058
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e9da9bf2a52a4a6da9fd0d364b822058
record_format	dspace
spelling	oai:doaj.org-article:e9da9bf2a52a4a6da9fd0d364b8220582021-12-02T16:06:07ZForecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks10.1038/s41545-021-00125-22059-7037https://doaj.org/article/e9da9bf2a52a4a6da9fd0d364b8220582021-06-01T00:00:00Zhttps://doi.org/10.1038/s41545-021-00125-2https://doaj.org/toc/2059-7037Abstract Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. We used ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration and to develop point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. We built ANN ensemble models using data from three refugee settlements and found that the risk-based FRC targets generated by the ensemble models were consistent with an empirical water safety evaluation, indicating that the models accurately predicted the risk of low point-of-consumption FRC despite all ensemble forecasts being underdispersed even after post-processing. This demonstrates the usefulness of ANN ensembles for generating risk-based point-of-distribution FRC targets to ensure safe drinking water in humanitarian operations.Michael De SantiUsman T. KhanMatthew ArnoldJean-François FesseletSyed Imran AliNature PortfolioarticleWater supply for domestic and industrial purposesTD201-500ENnpj Clean Water, Vol 4, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Water supply for domestic and industrial purposes TD201-500
spellingShingle	Water supply for domestic and industrial purposes TD201-500 Michael De Santi Usman T. Khan Matthew Arnold Jean-François Fesselet Syed Imran Ali Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
description	Abstract Waterborne illnesses are a leading health concern in refugee and internally displaced person (IDP) settlements where waterborne pathogens often spread through household recontamination of stored water. Ensuring sufficient chlorine residual is important for protecting drinking water against recontamination and ensuring water remains safe up to the point-of-consumption. We used ensembles of artificial neural networks (ANNs) to probabilistically forecast the point-of-consumption free residual chlorine (FRC) concentration and to develop point-of-distribution FRC targets based on the risk of insufficient FRC at the point-of consumption. We built ANN ensemble models using data from three refugee settlements and found that the risk-based FRC targets generated by the ensemble models were consistent with an empirical water safety evaluation, indicating that the models accurately predicted the risk of low point-of-consumption FRC despite all ensemble forecasts being underdispersed even after post-processing. This demonstrates the usefulness of ANN ensembles for generating risk-based point-of-distribution FRC targets to ensure safe drinking water in humanitarian operations.
format	article
author	Michael De Santi Usman T. Khan Matthew Arnold Jean-François Fesselet Syed Imran Ali
author_facet	Michael De Santi Usman T. Khan Matthew Arnold Jean-François Fesselet Syed Imran Ali
author_sort	Michael De Santi
title	Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
title_short	Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
title_full	Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
title_fullStr	Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
title_full_unstemmed	Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
title_sort	forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e9da9bf2a52a4a6da9fd0d364b822058
work_keys_str_mv	AT michaeldesanti forecastingpointofconsumptionchlorineresidualinrefugeesettlementsusingensemblesofartificialneuralnetworks AT usmantkhan forecastingpointofconsumptionchlorineresidualinrefugeesettlementsusingensemblesofartificialneuralnetworks AT matthewarnold forecastingpointofconsumptionchlorineresidualinrefugeesettlementsusingensemblesofartificialneuralnetworks AT jeanfrancoisfesselet forecastingpointofconsumptionchlorineresidualinrefugeesettlementsusingensemblesofartificialneuralnetworks AT syedimranali forecastingpointofconsumptionchlorineresidualinrefugeesettlementsusingensemblesofartificialneuralnetworks
_version_	1718385121545945088

Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks

Ejemplares similares