Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters
Sub-micron aerosols are a vital air pollutant to be measured because they pose health effects. These particles are quantified as particle number concentration (PN). However, PN measurements are not always available in air quality measurement stations, leading to data scarcity. In order to compensate...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/10/2876 |
_version_ | 1797567562149527552 |
---|---|
author | Martha A. Zaidan Ola Surakhi Pak Lun Fung Tareq Hussein |
author_facet | Martha A. Zaidan Ola Surakhi Pak Lun Fung Tareq Hussein |
author_sort | Martha A. Zaidan |
collection | DOAJ |
description | Sub-micron aerosols are a vital air pollutant to be measured because they pose health effects. These particles are quantified as particle number concentration (PN). However, PN measurements are not always available in air quality measurement stations, leading to data scarcity. In order to compensate this, PN modeling needs to be developed. This paper presents a PN modeling framework using sensitivity analysis tested on a one year aerosol measurement campaign conducted in Amman, Jordan. The method prepares a set of different combinations of all measured meteorological parameters to be descriptors of PN concentration. In this case, we resort to artificial neural networks in the forms of a feed-forward neural network (FFNN) and a time-delay neural network (TDNN) as modeling tools, and then, we attempt to find the best descriptors using all these combinations as model inputs. The best modeling tools are FFNN for daily averaged data (with R<inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mrow></mrow> <mn>2</mn> </msup> <mo>=</mo> <mn>0.77</mn> </mrow> </semantics> </math> </inline-formula>) and TDNN for hourly averaged data (with R<inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mrow></mrow> <mn>2</mn> </msup> <mo>=</mo> <mn>0.66</mn> </mrow> </semantics> </math> </inline-formula>) where the best combinations of meteorological parameters are found to be temperature, relative humidity, pressure, and wind speed. As the models follow the patterns of diurnal cycles well, the results are considered to be satisfactory. When PN measurements are not directly available or there are massive missing PN concentration data, PN models can be used to estimate PN concentration using available measured meteorological parameters. |
first_indexed | 2024-03-10T19:44:41Z |
format | Article |
id | doaj.art-59e437f846ba437199ee2f06d0d4cc3e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T19:44:41Z |
publishDate | 2020-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-59e437f846ba437199ee2f06d0d4cc3e2023-11-20T00:55:41ZengMDPI AGSensors1424-82202020-05-012010287610.3390/s20102876Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological ParametersMartha A. Zaidan0Ola Surakhi1Pak Lun Fung2Tareq Hussein3Institute for Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, FI-00560 Helsinki, FinlandDepartment of Computer Science, The University of Jordan, Amman 11942, JordanInstitute for Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, FI-00560 Helsinki, FinlandInstitute for Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, FI-00560 Helsinki, FinlandSub-micron aerosols are a vital air pollutant to be measured because they pose health effects. These particles are quantified as particle number concentration (PN). However, PN measurements are not always available in air quality measurement stations, leading to data scarcity. In order to compensate this, PN modeling needs to be developed. This paper presents a PN modeling framework using sensitivity analysis tested on a one year aerosol measurement campaign conducted in Amman, Jordan. The method prepares a set of different combinations of all measured meteorological parameters to be descriptors of PN concentration. In this case, we resort to artificial neural networks in the forms of a feed-forward neural network (FFNN) and a time-delay neural network (TDNN) as modeling tools, and then, we attempt to find the best descriptors using all these combinations as model inputs. The best modeling tools are FFNN for daily averaged data (with R<inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mrow></mrow> <mn>2</mn> </msup> <mo>=</mo> <mn>0.77</mn> </mrow> </semantics> </math> </inline-formula>) and TDNN for hourly averaged data (with R<inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mrow></mrow> <mn>2</mn> </msup> <mo>=</mo> <mn>0.66</mn> </mrow> </semantics> </math> </inline-formula>) where the best combinations of meteorological parameters are found to be temperature, relative humidity, pressure, and wind speed. As the models follow the patterns of diurnal cycles well, the results are considered to be satisfactory. When PN measurements are not directly available or there are massive missing PN concentration data, PN models can be used to estimate PN concentration using available measured meteorological parameters.https://www.mdpi.com/1424-8220/20/10/2876particle number concentrationmodelingsensitivity analysisartificial neural networksfeed-forward neural networktime-delay neural network |
spellingShingle | Martha A. Zaidan Ola Surakhi Pak Lun Fung Tareq Hussein Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters Sensors particle number concentration modeling sensitivity analysis artificial neural networks feed-forward neural network time-delay neural network |
title | Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters |
title_full | Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters |
title_fullStr | Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters |
title_full_unstemmed | Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters |
title_short | Sensitivity Analysis for Predicting Sub-Micron Aerosol Concentrations Based on Meteorological Parameters |
title_sort | sensitivity analysis for predicting sub micron aerosol concentrations based on meteorological parameters |
topic | particle number concentration modeling sensitivity analysis artificial neural networks feed-forward neural network time-delay neural network |
url | https://www.mdpi.com/1424-8220/20/10/2876 |
work_keys_str_mv | AT marthaazaidan sensitivityanalysisforpredictingsubmicronaerosolconcentrationsbasedonmeteorologicalparameters AT olasurakhi sensitivityanalysisforpredictingsubmicronaerosolconcentrationsbasedonmeteorologicalparameters AT paklunfung sensitivityanalysisforpredictingsubmicronaerosolconcentrationsbasedonmeteorologicalparameters AT tareqhussein sensitivityanalysisforpredictingsubmicronaerosolconcentrationsbasedonmeteorologicalparameters |