PuSH - Publication Server of Helmholtz Zentrum München: Ensemble machine learning, deep learning, and time series forecasting: Improving prediction accuracy for hourly concentrations of ambient air pollutants.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Petric, V.* ; Hussain, H.* ; Casni, K.* ; Vuckovic, M.* ; Schopper, A.* ; Andrijic, Z.U.* ; Kecorius, S. ; Madueno, L.* ; Kern, R.* ; Lovrić, M.*

Ensemble machine learning, deep learning, and time series forecasting: Improving prediction accuracy for hourly concentrations of ambient air pollutants.

Aerosol Air Qual. Res. 24:230317 (2024)

Publ. Version/Full Text

DOI

	Open Access Gold (Paid Option)

Abstract
Metrics
Extra information

This study aims to improve the generalisation capabilities of machine learning models for modelling hourly air pollutant concentrations in scenarios where access to high-quality data is limited. A diverse set of techniques was implemented to tackle this challenge, encompassing the utilisation of the prophet, random forest, and three different deep learning architectures: long short-term memory networks, convolutional neural networks, and multilayer perceptrons. A hybrid model of random forest and prophet was also tested. The role of the hybrid model was to combine the forecasting strengths of the Prophet model with the predictive power of the Random Forest model to better capture complex temporal patterns in the data. After testing, the hybrid model demonstrated improved generalization capabilities, achieving statistically significant improvements in R 2 for hourly concentrations of NO (improving by 26%), NO2 (enhancing by 18%), PM10 (with changes ranging from an 8% decline to a 35% improvement), and O3 (showcasing R 2 coefficients ranging from 0.83 to 0.87) at five sites in Graz, Austria. The utilisation of surface atmospheric ERA5-Land datasets within the models as model features showed high feature post hoc importance in the best (hybrid) models per pollutant and site. Furthermore, error analysis was performed to understand better the conditions under which these models might fail. The results showed that despite the expectations for models to fail with an increasing timeframe (the test set) from March 2019 to March 2020, the models were sufficiently stable for long-term prediction and thus can be used to forecast and predict air pollution.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Prophet; Ozone; Air pollution; LSTM; CNN; Random forests; Pollution; Ozone; Model

ISSN (print) / ISBN 1680-8584

e-ISSN 2071-1409

Journal Aerosol and Air Quality Research

Quellenangaben Volume: 24, Issue: 12, Article Number: 230317

Publisher Tainan

Publishing Place Chaoyang Univ Tech, Dept Env Eng & Mgmt, Prod Ctr Aaqr, No 168, Jifong E Rd, Wufong Township, Taichung County, 41349, Taiwan

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Institute of Epidemiology (EPI)

Grants BMK
BMAW
Province Styria
Province Vienna
Province Tyrol