Filling gaps in PM2.5 time series: A broad evaluation from statistical to advanced neural network models
PLOS One · 14.08.2025 · 20 (8) · e0330211
DOI: 10.1371/journal.pone.0330211 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 14.08.2025. Verfasst von Ruslan Safarov und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, Faculty of Natural Sciences, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan. Hauptthemen laut MEDLINE: Particulate Matter, Neural Networks, Computer, Environmental Monitoring, Models, Statistical. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Higher Education of the Republic of Kazakhstan.
Abstract (Originalsprache)
This study addressed the critical challenge of filling gaps in PM2.5 time series data from Pavlodar, Kazakhstan. We developed and evaluated a comprehensive hierarchy of 46 gap-filling methods across five representative gap lengths (5–72 hours), introducing dynamic models capable of adapting to gaps of variable duration. Tree-based models with bidirectional sequence-to-sequence architectures delivered superior performance, with XGB Seq2Seq achieving a mean absolute error of 5.231 ± 0.292 μg/m 3 for 12-hour gaps, representing a 63% improvement over basic statistical methods. The advantage of multivariate models incorporating meteorological variables increased substantially with gap length, from modest improvements of 2–3% for 5-hour gaps to significant enhancements of 16–18% for 48–72 hour gaps. Dynamic multivariate models demonstrated remarkable operational flexibility by successfully processing real-world gaps ranging from 1 to 191 hours despite being trained on maximum lengths of 72 hours. Analysis of the reconstructed complete time series revealed that 61.2% of monitored hours exceeded the WHO daily threshold of 15 μg/m 3 , with strong seasonal patterns and pronounced diurnal cycles. This research advances environmental monitoring capabilities by providing robust methodological tools for addressing data continuity challenges that currently limit the utility of PM2.5 measurements for public health applications and scientific analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Chemistry, Faculty of Natural Sciences, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan.
- Department of Chemistry and Chemical Technology, Kh. Dosmukhamedov Atyrau University, Atyrau, Kazakhstan.
- Higher School of Natural Science, Margulan University, Pavlodar, Kazakhstan.
- Association of legal entities «Petrochemical Products Producers and Consumers Association (Petrochemical Association)», Astana, Kazakhstan.
- Department of Science, Faculty of Natural Sciences, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan.
ORCID-Profile: Ruslan Safarov, Eldar Kopishev
Förderung
- Ministry of Science and Higher Education of the Republic of Kazakhstan
Zitieren
APA
Safarov, R., Shomanova, Z., Nossenko, Y., Kopishev, E., Bexeitova, Z., & Kamatov, R. (2025). Filling gaps in PM2.5 time series: A broad evaluation from statistical to advanced neural network models. PLOS One, 20(8), e0330211. https://doi.org/10.1371/journal.pone.0330211
Vancouver
Safarov R, Shomanova Z, Nossenko Y, Kopishev E, Bexeitova Z, Kamatov R. Filling gaps in PM2.5 time series: A broad evaluation from statistical to advanced neural network models. PLOS One. 2025;20(8):e0330211. doi:10.1371/journal.pone.0330211
BibTeX
@article{Safarov2025,
author = {Safarov, Ruslan and Shomanova, Zhanat and Nossenko, Yuriy and Kopishev, Eldar and Bexeitova, Zhuldyz and Kamatov, Ruslan},
title = {Filling gaps in PM2.5 time series: A broad evaluation from statistical to advanced neural network models},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {8},
pages = {e0330211},
doi = {10.1371/journal.pone.0330211}
}
EUVIMED