A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME

Elena Fillola*, Raul Santos-Rodriguez, Alistair Manning, Simon O'Doherty, Matt Rigby

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

1 Citation (Scopus)

Abstract

Lagrangian particle dispersion models (LPDMs) have been used extensively to calculate source-receptor relationships (“footprints”) for use in applications such as greenhouse gas (GHG) flux inversions. Because a single model simulation is required for each data point, LPDMs do not scale well to applications with large data sets such as flux inversions using satellite observations. Here, we develop a proof-of-concept machine learning emulator for LPDM footprints over a ∼ 350 km × 230 km region around an observation point, and test it for a range of in situ measurement sites from around the world. As opposed to previous approaches to footprint approximation, it does not require the interpolation or smoothing of footprints produced by the LPDM. Instead, the footprint is emulated entirely from meteorological inputs. This is achieved by independently emulating the footprint magnitude at each grid cell in the domain using gradient-boosted regression trees with a selection of meteorological variables as inputs. The emulator is trained based on footprints from the UK Met Office's Numerical Atmospheric-dispersion Modelling Environment (NAME) for 2014 and 2015, and the emulated footprints are evaluated against hourly NAME output from 2016 and 2020. When compared to CH4 concentration time series generated by NAME, we show that our emulator achieves a mean R-squared score of 0.69 across all sites investigated between 2016 and 2020. The emulator can predict a footprint in around 10 ms, compared to around 10 min for the 3D simulator. This simple and interpretable proof-of-concept emulator demonstrates the potential of machine learning for LPDM emulation.
Original languageEnglish
Pages (from-to)1997-2009
Number of pages13
JournalGeoscientific Model Development
Volume16
Issue number7
DOIs
Publication statusPublished - 12 Apr 2023

Bibliographical note

Funding Information:
This research has been supported by the Natural Environment Research Council (grant no. NE/V002996/1), Google (PhD Fellowship 2021), and the UK Research and Innovation, Engineering and Physical Sciences Research Council (Turing AI Fellowship, grant no. EP/V024817/1).

Funding Information:
Elena Fillola was funded through a Google PhD Fellowship 2021. Matt Rigby was funded through the Natural Environment Research Council's Constructing a Digital Environment OpenGHG project (NE/V002996/1). Raul Santos-Rodriguez was funded by the UKRI EPSRC Turing AI Fellowship EP/V024817/1. Measurements from Mace Head were funded by the Advanced Global Atmospheric Gases Experiment (NASA grant NNX16AC98G) and measurements from the UK DECC network by the UK Department of Business, Energy & Industrial Strategy through contract 1537/06/2018 to the University of Bristol. Since 2017, measurements at Heathfield have been maintained by the National Physical Laboratory mainly under funding from the National Measurement System. This work was carried out using the computational facilities of the Advanced Computing Research Centre, University of Bristol – http://www.bristol.ac.uk/acrc/ (last access: April 2023).

Publisher Copyright:
© 2023 Copernicus GmbH. All rights reserved.

Fingerprint

Dive into the research topics of 'A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME'. Together they form a unique fingerprint.

Cite this