Estimation of Prediction Error in Regression Air Quality Models

Combustion of energy fuels or organic waste is associated with the emission of harmful gases and aerosols into the atmosphere, which strongly affects air quality. Air quality monitoring devices are unreliable and measurement gaps appear quite often. Missing data modeling techniques can be used to co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Szymon Hoffman
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	air monitoring air pollutants air quality models approximation error concentration modeling prediction Technology T
Acceso en línea:	https://doaj.org/article/6c2d96a0687d4863a3669d3517016f88
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6c2d96a0687d4863a3669d3517016f88
record_format	dspace
spelling	oai:doaj.org-article:6c2d96a0687d4863a3669d3517016f882021-11-11T16:06:03ZEstimation of Prediction Error in Regression Air Quality Models10.3390/en142173871996-1073https://doaj.org/article/6c2d96a0687d4863a3669d3517016f882021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7387https://doaj.org/toc/1996-1073Combustion of energy fuels or organic waste is associated with the emission of harmful gases and aerosols into the atmosphere, which strongly affects air quality. Air quality monitoring devices are unreliable and measurement gaps appear quite often. Missing data modeling techniques can be used to complete the monitoring data. Concentrations of monitored pollutants can be approximated with regression modeling tools, such as artificial neural networks. In this study, a long-term set of data from the air monitoring station in Zabrze (Silesia, South Poland) was analyzed. Concentration prediction was tested for the main air pollutants, i.e., O<sub>3</sub>, NO, NO<sub>2</sub>, SO<sub>2</sub>, PM<sub>10</sub>, CO. Multilayer perceptrons were used to model the concentrations. The predicted concentrations were compared to the observed ones to evaluate the approximation accuracy. Prediction errors were calculated separately for the whole concentration range as well as for the specified concentration subranges. Some different measures of error were estimated. It was stated that the use of a single measure of the approximation accuracy may lead to incorrect interpretation. The application of one neural network to the entire concentration range results in different prediction accuracy in various concentration subranges. Replacing one neural network with several networks adjusted to specific concentration subranges should improve the modeling accuracy.Szymon HoffmanMDPI AGarticleair monitoringair pollutantsair quality modelsapproximation errorconcentration modelingpredictionTechnologyTENEnergies, Vol 14, Iss 7387, p 7387 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	air monitoring air pollutants air quality models approximation error concentration modeling prediction Technology T
spellingShingle	air monitoring air pollutants air quality models approximation error concentration modeling prediction Technology T Szymon Hoffman Estimation of Prediction Error in Regression Air Quality Models
description	Combustion of energy fuels or organic waste is associated with the emission of harmful gases and aerosols into the atmosphere, which strongly affects air quality. Air quality monitoring devices are unreliable and measurement gaps appear quite often. Missing data modeling techniques can be used to complete the monitoring data. Concentrations of monitored pollutants can be approximated with regression modeling tools, such as artificial neural networks. In this study, a long-term set of data from the air monitoring station in Zabrze (Silesia, South Poland) was analyzed. Concentration prediction was tested for the main air pollutants, i.e., O<sub>3</sub>, NO, NO<sub>2</sub>, SO<sub>2</sub>, PM<sub>10</sub>, CO. Multilayer perceptrons were used to model the concentrations. The predicted concentrations were compared to the observed ones to evaluate the approximation accuracy. Prediction errors were calculated separately for the whole concentration range as well as for the specified concentration subranges. Some different measures of error were estimated. It was stated that the use of a single measure of the approximation accuracy may lead to incorrect interpretation. The application of one neural network to the entire concentration range results in different prediction accuracy in various concentration subranges. Replacing one neural network with several networks adjusted to specific concentration subranges should improve the modeling accuracy.
format	article
author	Szymon Hoffman
author_facet	Szymon Hoffman
author_sort	Szymon Hoffman
title	Estimation of Prediction Error in Regression Air Quality Models
title_short	Estimation of Prediction Error in Regression Air Quality Models
title_full	Estimation of Prediction Error in Regression Air Quality Models
title_fullStr	Estimation of Prediction Error in Regression Air Quality Models
title_full_unstemmed	Estimation of Prediction Error in Regression Air Quality Models
title_sort	estimation of prediction error in regression air quality models
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6c2d96a0687d4863a3669d3517016f88
work_keys_str_mv	AT szymonhoffman estimationofpredictionerrorinregressionairqualitymodels
_version_	1718432419600662528

Estimation of Prediction Error in Regression Air Quality Models

Ejemplares similares