Data Augmentation Strategies for Improved PM2.5 Forecasting Using Transformer Architectures
Atmosphere · 24.01.2025 · 16 (2) · 127
DOI: 10.3390/atmos16020127 ↗Kurz gefasst
Fachartikel in der Zeitschrift Atmosphere, online erschienen am 24.01.2025. Verfasst von Phoebe Pan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NASA AIST, NASA Goddard CISTO, NSF I/UCRC.
Abstract (Originalsprache)
Breathing in fine particulate matter of diameter less than 2.5 µm (PM2.5) greatly increases an individual’s risk of cardiovascular and respiratory diseases. As climate change progresses, extreme weather events, including wildfires, are expected to increase, exacerbating air pollution. However, models often struggle to capture extreme pollution events due to the rarity of high PM2.5 levels in training datasets. To address this, we implemented cluster-based undersampling and trained Transformer models to improve extreme event prediction using various cutoff thresholds (12.1 µg/m3 and 35.5 µg/m3) and partial sampling ratios (10/90, 20/80, 30/70, 40/60, 50/50). Our results demonstrate that the 35.5 µg/m3 threshold, paired with a 20/80 partial sampling ratio, achieved the best performance, with an RMSE of 2.080, MAE of 1.386, and R2 of 0.914, particularly excelling in forecasting high PM2.5 events. Overall, models trained on augmented data significantly outperformed those trained on original data, highlighting the importance of resampling techniques in improving air quality forecasting accuracy, especially for high-pollution scenarios. These findings provide critical insights into optimizing air quality forecasting models, enabling more reliable predictions of extreme pollution events. By advancing the ability to forecast high PM2.5 levels, this study contributes to the development of more informed public health and environmental policies to mitigate the impacts of air pollution, and advanced the technology for building better air quality digital twins.
Förderung
- NASA AIST
- NASA Goddard CISTO
- NSF I/UCRC
Zitieren
APA
Pan, P., Malarvizhi, A. S., & Yang, C. (2025). Data Augmentation Strategies for Improved PM2.5 Forecasting Using Transformer Architectures. Atmosphere, 16(2), 127. https://doi.org/10.3390/atmos16020127
Vancouver
Pan P, Malarvizhi AS, Yang C. Data Augmentation Strategies for Improved PM2.5 Forecasting Using Transformer Architectures. Atmosphere. 2025;16(2):127. doi:10.3390/atmos16020127
BibTeX
@article{Pan2025,
author = {Pan, Phoebe and Malarvizhi, Anusha Srirenganathan and Yang, Chaowei},
title = {Data Augmentation Strategies for Improved PM2.5 Forecasting Using Transformer Architectures},
journal = {Atmosphere},
year = {2025},
volume = {16},
number = {2},
pages = {127},
doi = {10.3390/atmos16020127}
}
EUVIMED