PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Poelzl, M.* ; Kern, R.* ; Kecorius, S. ; Lovrić, M.*

Exploration of transfer learning techniques for the prediction of PM10.

Sci. Rep. 15:2919 (2025)
Verlagsversion Forschungsdaten DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
Modelling of pollutants provides valuable insights into air quality dynamics, aiding exposure assessment where direct measurements are not viable. Machine learning (ML) models can be employed to explore such dynamics, including the prediction of air pollution concentrations, yet demanding extensive training data. To address this, techniques like transfer learning (TL) leverage knowledge from a model trained on a rich dataset to enhance one trained on a sparse dataset, provided there are similarities in data distribution. In our experimental setup, we utilize meteorological and pollutant data from multiple governmental air quality measurement stations in Graz, Austria, supplemented by data from one station in Zagreb, Croatia to simulate data scarcity. Common ML models such as Random Forests, Multilayer Perceptrons, Long-Short-Term Memory, and Convolutional Neural Networks are explored to predict particulate matter in both cities. Our detailed analysis of PM10 suggests that similarities between the cities and the meteorological features exist and can be further exploited. Hence, TL appears to offer a viable approach to enhance PM10 predictions for the Zagreb station, despite the challenges posed by data scarcity. Our results demonstrate the feasibility of different TL techniques to improve particulate matter prediction on transferring a ML model trained from all stations of Graz and transferred to Zagreb. Through our investigation, we discovered that selectively choosing time spans based on seasonal patterns not only aids in reducing the amount of data needed for successful TL but also significantly improves prediction performance. Specifically, training a Random Forest model using data from all measurement stations in Graz and transferring it with only 20% of the labelled data from Zagreb resulted in a 22% enhancement compared to directly testing the trained model on Zagreb.
Impact Factor
Scopus SNIP
Altmetric
3.900
0.000
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Pollution
Sprache englisch
Veröffentlichungsjahr 2025
HGF-Berichtsjahr 2025
ISSN (print) / ISBN 2045-2322
e-ISSN 2045-2322
Zeitschrift Scientific Reports
Quellenangaben Band: 15, Heft: 1, Seiten: , Artikelnummer: 2919 Supplement: ,
Verlag Nature Publishing Group
Verlagsort London
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Epidemiology (EPI)
POF Topic(s) 30202 - Environmental Health
Forschungsfeld(er) Genetics and Epidemiology
PSP-Element(e) G-504000-004
Förderungen European Commission
EU-Commission Grant
Austrian COMET Program-Competence Centers for Excellent Technologies-under the auspices of the Austrian Federal Ministry for Climate Action, Environment, Energy, Mobility, Innovation and Technology (BMK)
Austrian Federal Ministry for Digital and Economic Affairs (BMDW)
State of Styria
DOI 10.1038/s41598-025-86550-6
WOS ID 001405681100016
Scopus ID 85216717796
PubMed ID 39849002
Erfassungsdatum 2025-03-25
[➜Korrektur melden]