GMDD

Geoscientific Model Development Discussions

GMDD

Geosci. Model Dev. Discuss.

1991-962X

Göttingen, Germany

10.5194/gmd-2020-270

Evaluating the use of Facebook's Prophet model v0.6 in forecasting concentrations of NO2 at single sites across the UK and in response to the COVID-19 lockdown in Manchester, England

Topping

David

https://orcid.org/0000-0001-8247-9649

¹ Watts

David

² Coe

Hugh

https://orcid.org/0000-0002-3264-1713

¹ Evans

James

³ Bannan

Thomas J.

https://orcid.org/0000-0002-1760-6522

¹ Lowe

Douglas

https://orcid.org/0000-0002-1248-3594

⁴ Jay

Caroline

⁵ Taylor

Jonathan W.

https://orcid.org/0000-0002-2120-186X

Department of Earth and Environmental Science, The University of Manchester, Oxford Road, Manchester, M13 9PL

Transport for Greater Manchester, 2 Piccadilly Place, Manchester, M1 3BG

Department of Geography, The University of Manchester, Oxford Road, Manchester, M13 9PL

ResearchIT, The University of Manchester, Oxford Road, Manchester, M13 9PL

Department of Computer Science, The University of Manchester, Oxford Road, Manchester, M13 9PL

Engineering and Physical Sciences Research Council

EP/P016782/1

Alan Turing Institute

Understanding the relationship between human health and the environment

02 09 2020

2020 1 22

2020

This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

This article is available from https://gmd.copernicus.org/preprints/gmd-2020-270/

The full text article is available as a PDF file from https://gmd.copernicus.org/preprints/gmd-2020-270/gmd-2020-270.pdf

Time-series forecasting methods have often been used to mitigate some of the challenges associated with deploying chemical transport models at high resolution for use at local scales. In this study we deploy and evaluate Facebook’s Prophet model v0.6 in predicting hourly concentrations of Nitrogen Dioxide [NO2] over a 2 year period [2018–2019] across the UK’s Automatic Urban and Rural Network (AURN). Results indicate promising performance when comparing absolute values, diurnal trends and seasonality, with discrepancies increasing when the site is classified as having a larger contribution from regional sources and non-local sources. Using mobility and traffic volume data in the model fitting process allowed us to evaluate the ability of the model to forecast levels at two sites in Manchester where there were significant reductions in traffic levels during the COVID-19 lock-down, defined as a national state of restricted access. Prior to lock-down, comparison between hourly concentrations from the Prophet forecast and observations are significantly better compared with predictions from the EMEP regional model. Despite the simplified approach of fitting to derived NO2-per-traffic volume over a 5 year period, trends in absolute NO2 reductions and diurnal profiles were captured well at Manchester Piccadilly. However at a second site, in Sharston, we found that reliance on historical NO2-per-traffic volume resulted in errors in the prediction as the nature of local traffic changed under the COVID-19 lock-down; correlating with an increase in the Heavy Goods Vehicle fleet [HGV] relative to other forms of traffic. Ancillary meteorological information and predictions from the EMEP model enabled identification of significant contributions from regional sources during the lock-down period. These periods coincide with noticeable differences between measured and forecast values from Prophet. Overall the Prophet model offers a relatively effective and simple way to make predictions about NO2 at local levels. The source code to reproduce and expand on the work presented in this paper is made openly available.