Development of PM2.5 Forecast Model Combining ConvLSTM and DNN in Seoul
Atmosphere · 25.10.2024 · 15 (11) · 1276
DOI: 10.3390/atmos15111276 ↗Kurz gefasst
Fachartikel in der Zeitschrift Atmosphere, online erschienen am 25.10.2024. Verfasst von Ji-Seok Koo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Particulate Matter Management Specialized Graduate Program.
Abstract (Originalsprache)
Accurate prediction of PM2.5 concentrations is essential for public health management, especially in areas affected by long-range pollutant transport. This study presents a hybrid model combining convolutional long short-term memory (ConvLSTM) and deep neural networks (DNNs) to enhance PM2.5 forecasting in Seoul, South Korea. The hybrid model leverages ConvLSTM’s ability to capture spatiotemporal dependencies and DNN’s strength in feature extraction, enabling it to outperform standalone CMAQ and DNN models. For the T1 forecast (6 h averages), the ConvLSTM-DNN model exhibited superior performance, with an RMSE of 7.2 µg/m3 compared to DNN’s 8.5 µg/m3 and CMAQ’s 10.1 µg/m3. The model also maintained high categorical accuracy (ACC) and probability of detection (POD) for critical PM2.5 levels while reducing false alarms (FARs), particularly in bad and very bad events. Although its performance decreases over extended forecast periods, the ConvLSTM-DNN model demonstrates its utility as a robust forecasting tool. Future work will focus on optimizing the network structure to improve long-term forecast accuracy.
Förderung
- Particulate Matter Management Specialized Graduate Program
Zitieren
APA
Koo, J., Wang, K., Yun, H., Kwon, H., & Koo, Y. (2024). Development of PM2.5 Forecast Model Combining ConvLSTM and DNN in Seoul. Atmosphere, 15(11), 1276. https://doi.org/10.3390/atmos15111276
Vancouver
Koo J, Wang K, Yun H, Kwon H, Koo Y. Development of PM2.5 Forecast Model Combining ConvLSTM and DNN in Seoul. Atmosphere. 2024;15(11):1276. doi:10.3390/atmos15111276
BibTeX
@article{Koo2024,
author = {Koo, Ji-Seok and Wang, Kyung-Hui and Yun, Hui-Young and Kwon, Hee-Yong and Koo, Youn-Seo},
title = {Development of PM2.5 Forecast Model Combining ConvLSTM and DNN in Seoul},
journal = {Atmosphere},
year = {2024},
volume = {15},
number = {11},
pages = {1276},
doi = {10.3390/atmos15111276}
}
EUVIMED