Regression Modeling of Daily PM 2.5 Concentrations with a Multilayer Perceptron

Szymon Hoffman (), Rafał Jasiński and Janusz Baran
Additional contact information
Szymon Hoffman: Faculty of Infrastructure and Environment, Czestochowa University of Technology, 69 Dabrowskiego St., 42-200 Czestochowa, Poland
Rafał Jasiński: Faculty of Infrastructure and Environment, Czestochowa University of Technology, 69 Dabrowskiego St., 42-200 Czestochowa, Poland
Janusz Baran: Faculty of Electrical Engineering, Czestochowa University of Technology, 17 Armii Krajowej, 42-200 Czestochowa, Poland

Energies, 2024, vol. 17, issue 9, 1-20

Abstract: Various types of energetic fuel combustion processes emit dangerous pollutants into the air, including aerosol particles, marked as PM 10 . Routine air quality monitoring includes determining the PM 10 concentration as one of the basic measurements. At some air monitoring stations, the PM 10 measurement is supplemented by the simultaneous determination of the concentration of PM 2.5 as a finer fraction of suspended particles. Since the PM 2.5 fraction has a significant share in the PM 10 fraction, the concentrations of both types of particles should be strongly correlated, and the concentrations of one of these fractions can be used to model the concentrations of the other fraction. The aim of the study was to assess the error of predicting PM 2.5 concentration using PM 10 concentration as the main predictor. The analyzed daily concentrations were measured at 11 different monitoring stations in Poland and covered the period 2010–2021. MLP (multilayer perceptron) artificial neural networks were used to approximate the daily PM 2.5 concentrations. PM 10 concentrations and time variables were tested as predictors in neural networks. Several different prediction errors were taken as measures of modeling quality. Depending on the monitoring station, in models with one PM 10 predictor, the RMSE error values were in the range of 2.31–6.86 μg/m 3 . After taking into account the second predictor D (date), the corresponding RMSE errors were lower and were in the range of 2.06–5.54 μg/m 3 . Our research aimed to find models that were as simple and universal as possible. In our models, the main predictor is the PM 10 concentration; therefore, the only condition to be met is monitoring the measurement of PM 10 concentrations. We showed that models trained at other air monitoring stations, so-called foreign models, can be successfully used to approximate PM 2.5 concentrations at another station.

Keywords: air protection; air monitoring; environmental management; air quality modeling; particular matter; PM 2.5 prediction; regression models; artificial neural networks; multilayer perceptrons (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/9/2202/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/9/2202/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:9:p:2202-:d:1388250

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().