Browse by author
Lookup NU author(s): Adam Booth, Professor Philip JamesORCiD, Dr Stephen McGough, Dr Ellis SolaimanORCiD
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Accurately forecasting air quality could lead to the development of dynamic, data-driven policy-making and improved early warning detection systems. Deep learning has demonstrated the potential to produce highly accurate forecasting models, but it is noted that much literature focuses on narrow datasets and typically considers one geographic area. In this research, three diverse air quality datasets are utilised to evaluate four deep learning algorithms, which are feedforward neural networks, Long Short-Term Memory (LSTM) recurrent neural networks, DeepAR and Temporal Fusion Transformers (TFTs). The study uses these modules to forecast CO, NO2, O3, and particulate matter 2.5 and 10 (PM2.5, PM10) individually, producing a 24 h forecast for a given sensor and pollutant. Each model is optimised using a hyperparameter and a feature selection process, evaluating the utility of exogenous data such as meteorological data, including wind speed and temperature, along with the inclusion of other pollutants. The findings show that the TFT and DeepAR algorithms achieve superior performance over their simpler counterparts, though they may prove challenging in practical applications. It is noted that while some covariates such as CO are important covariates for predicting NO2 across all three datasets, other parameters such as context length proved inconsistent across the three areas, suggesting that parameters such as context length are location and pollutant specific.
Author(s): Booth A, James P, McGough S, Solaiman E
Publication type: Article
Publication status: Published
Journal: Forcasting
Year: 2025
Volume: 7
Issue: 4
Print publication date: 05/11/2025
Online publication date: 05/11/2025
Acceptance date: 17/10/2025
Date deposited: 23/12/2025
ISSN (electronic): 2571-9394
Publisher: MDPI
URL: https://doi.org/10.3390/forecast7040066
DOI: 10.3390/forecast7040066
Data Access Statement: The data supporting the findings of this study are available from the corresponding author upon request.
Altmetrics provided by Altmetric
