Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Philipp Otto
  • Alessandro Fusta Moro
  • Jacopo Rodeschini
  • Qendrim Shaboviq
  • Rosaria Ignaccolo
  • Natalia Golini
  • Michela Cameletti
  • Paolo Maranzano
  • Francesco Finazzi
  • Alessandro Fassò

External Research Organisations

  • University of Glasgow
  • Universita di Bergamo (UniBg)
  • University of Turin
  • University of Milan - Bicocca
  • Fondazione Eni Enrico Mattei (FEEM)
View graph of relations

Details

Original languageEnglish
Pages (from-to)245-272
Number of pages28
JournalEnvironmental and Ecological Statistics
Volume31
Issue number2
Early online date1 Feb 2024
Publication statusPublished - Jun 2024

Abstract

This study presents a comparative analysis of three predictive models with an increasing degree of flexibility: hidden dynamic geostatistical models (HDGM), generalised additive mixed models (GAMM), and the random forest spatiotemporal kriging models (RFSTK). These models are evaluated for their effectiveness in predicting PM 2.5 concentrations in Lombardy (North Italy) from 2016 to 2020. Despite differing methodologies, all models demonstrate proficient capture of spatiotemporal patterns within air pollution data with similar out-of-sample performance. Furthermore, the study delves into station-specific analyses, revealing variable model performance contingent on localised conditions. Model interpretation, facilitated by parametric coefficient analysis and partial dependence plots, unveils consistent associations between predictor variables and PM 2.5 concentrations. Despite nuanced variations in modelling spatiotemporal correlations, all models effectively accounted for the underlying dependence. In summary, this study underscores the efficacy of conventional techniques in modelling correlated spatiotemporal data, concurrently highlighting the complementary potential of Machine Learning and classical statistical approaches.

Keywords

    Air pollution, Generalised additive mixed model, Geostatistics, Hidden dynamic geostatistical model, Machine learning, Random forest spatiotemporal kriging, Spatiotemporal process

ASJC Scopus subject areas

Cite this

Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study. / Otto, Philipp; Fusta Moro, Alessandro; Rodeschini, Jacopo et al.
In: Environmental and Ecological Statistics, Vol. 31, No. 2, 06.2024, p. 245-272.

Research output: Contribution to journalArticleResearchpeer review

Otto, P, Fusta Moro, A, Rodeschini, J, Shaboviq, Q, Ignaccolo, R, Golini, N, Cameletti, M, Maranzano, P, Finazzi, F & Fassò, A 2024, 'Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study', Environmental and Ecological Statistics, vol. 31, no. 2, pp. 245-272. https://doi.org/10.1007/s10651-023-00589-0
Otto, P., Fusta Moro, A., Rodeschini, J., Shaboviq, Q., Ignaccolo, R., Golini, N., Cameletti, M., Maranzano, P., Finazzi, F., & Fassò, A. (2024). Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study. Environmental and Ecological Statistics, 31(2), 245-272. https://doi.org/10.1007/s10651-023-00589-0
Otto P, Fusta Moro A, Rodeschini J, Shaboviq Q, Ignaccolo R, Golini N et al. Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study. Environmental and Ecological Statistics. 2024 Jun;31(2):245-272. Epub 2024 Feb 1. doi: 10.1007/s10651-023-00589-0
Otto, Philipp ; Fusta Moro, Alessandro ; Rodeschini, Jacopo et al. / Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy) : a comparative study. In: Environmental and Ecological Statistics. 2024 ; Vol. 31, No. 2. pp. 245-272.
Download
@article{8fa144396eb54d59bdb4acf0958dc672,
title = "Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy): a comparative study",
abstract = "This study presents a comparative analysis of three predictive models with an increasing degree of flexibility: hidden dynamic geostatistical models (HDGM), generalised additive mixed models (GAMM), and the random forest spatiotemporal kriging models (RFSTK). These models are evaluated for their effectiveness in predicting PM 2.5 concentrations in Lombardy (North Italy) from 2016 to 2020. Despite differing methodologies, all models demonstrate proficient capture of spatiotemporal patterns within air pollution data with similar out-of-sample performance. Furthermore, the study delves into station-specific analyses, revealing variable model performance contingent on localised conditions. Model interpretation, facilitated by parametric coefficient analysis and partial dependence plots, unveils consistent associations between predictor variables and PM 2.5 concentrations. Despite nuanced variations in modelling spatiotemporal correlations, all models effectively accounted for the underlying dependence. In summary, this study underscores the efficacy of conventional techniques in modelling correlated spatiotemporal data, concurrently highlighting the complementary potential of Machine Learning and classical statistical approaches.",
keywords = "Air pollution, Generalised additive mixed model, Geostatistics, Hidden dynamic geostatistical model, Machine learning, Random forest spatiotemporal kriging, Spatiotemporal process",
author = "Philipp Otto and {Fusta Moro}, Alessandro and Jacopo Rodeschini and Qendrim Shaboviq and Rosaria Ignaccolo and Natalia Golini and Michela Cameletti and Paolo Maranzano and Francesco Finazzi and Alessandro Fass{\`o}",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",
year = "2024",
month = jun,
doi = "10.1007/s10651-023-00589-0",
language = "English",
volume = "31",
pages = "245--272",
journal = "Environmental and Ecological Statistics",
issn = "1352-8505",
publisher = "Springer Netherlands",
number = "2",

}

Download

TY - JOUR

T1 - Spatiotemporal modelling of PM 2.5 concentrations in Lombardy (Italy)

T2 - a comparative study

AU - Otto, Philipp

AU - Fusta Moro, Alessandro

AU - Rodeschini, Jacopo

AU - Shaboviq, Qendrim

AU - Ignaccolo, Rosaria

AU - Golini, Natalia

AU - Cameletti, Michela

AU - Maranzano, Paolo

AU - Finazzi, Francesco

AU - Fassò, Alessandro

N1 - Publisher Copyright: © The Author(s) 2024.

PY - 2024/6

Y1 - 2024/6

N2 - This study presents a comparative analysis of three predictive models with an increasing degree of flexibility: hidden dynamic geostatistical models (HDGM), generalised additive mixed models (GAMM), and the random forest spatiotemporal kriging models (RFSTK). These models are evaluated for their effectiveness in predicting PM 2.5 concentrations in Lombardy (North Italy) from 2016 to 2020. Despite differing methodologies, all models demonstrate proficient capture of spatiotemporal patterns within air pollution data with similar out-of-sample performance. Furthermore, the study delves into station-specific analyses, revealing variable model performance contingent on localised conditions. Model interpretation, facilitated by parametric coefficient analysis and partial dependence plots, unveils consistent associations between predictor variables and PM 2.5 concentrations. Despite nuanced variations in modelling spatiotemporal correlations, all models effectively accounted for the underlying dependence. In summary, this study underscores the efficacy of conventional techniques in modelling correlated spatiotemporal data, concurrently highlighting the complementary potential of Machine Learning and classical statistical approaches.

AB - This study presents a comparative analysis of three predictive models with an increasing degree of flexibility: hidden dynamic geostatistical models (HDGM), generalised additive mixed models (GAMM), and the random forest spatiotemporal kriging models (RFSTK). These models are evaluated for their effectiveness in predicting PM 2.5 concentrations in Lombardy (North Italy) from 2016 to 2020. Despite differing methodologies, all models demonstrate proficient capture of spatiotemporal patterns within air pollution data with similar out-of-sample performance. Furthermore, the study delves into station-specific analyses, revealing variable model performance contingent on localised conditions. Model interpretation, facilitated by parametric coefficient analysis and partial dependence plots, unveils consistent associations between predictor variables and PM 2.5 concentrations. Despite nuanced variations in modelling spatiotemporal correlations, all models effectively accounted for the underlying dependence. In summary, this study underscores the efficacy of conventional techniques in modelling correlated spatiotemporal data, concurrently highlighting the complementary potential of Machine Learning and classical statistical approaches.

KW - Air pollution

KW - Generalised additive mixed model

KW - Geostatistics

KW - Hidden dynamic geostatistical model

KW - Machine learning

KW - Random forest spatiotemporal kriging

KW - Spatiotemporal process

UR - http://www.scopus.com/inward/record.url?scp=85183928401&partnerID=8YFLogxK

U2 - 10.1007/s10651-023-00589-0

DO - 10.1007/s10651-023-00589-0

M3 - Article

AN - SCOPUS:85183928401

VL - 31

SP - 245

EP - 272

JO - Environmental and Ecological Statistics

JF - Environmental and Ecological Statistics

SN - 1352-8505

IS - 2

ER -