07 Nov 2022
07 Nov 2022
Status: this preprint is open for discussion.

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

Elena Fillola1, Raul Santos-Rodriguez1, Alistair Manning2, Simon O'Doherty3, and Matt Rigby3 Elena Fillola et al.
  • 1Department of Engineering Mathematics, University of Bristol, Bristol, UK
  • 2Hadley Centre, Met Office, Exeter, UK
  • 3School of Chemistry, University of Bristol, Bristol, UK

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 by 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 (GBRTs) with a selection of meteorological variables as inputs. The emulator is trained based on footprints from the UK Met Office 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 minutes for the 3D simulator. This simple and interpretable proof-of-concept emulator demonstrates the potential of machine learning for LPDM emulation.

Elena Fillola et al.

Status: open (until 04 Jan 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Elena Fillola et al.

Elena Fillola et al.


Total article views: 416 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
315 97 4 416 3 1
  • HTML: 315
  • PDF: 97
  • XML: 4
  • Total: 416
  • BibTeX: 3
  • EndNote: 1
Views and downloads (calculated since 07 Nov 2022)
Cumulative views and downloads (calculated since 07 Nov 2022)

Viewed (geographical distribution)

Total article views: 334 (including HTML, PDF, and XML) Thereof 334 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 06 Dec 2022
Short summary
Lagrangian particle dispersion models are used extensively for the estimation of greenhouse gas (GHG) fluxes using atmospheric observations. However, these models do not scale well as data volumes increase. Here, we develop a proof-of-concept machine learning emulator that can produce outputs similar to those of the dispersion model, but 50,000 times faster, using only meteorological inputs. This works demonstrates the potential of machine learning to accelerate GHG estimations across the globe.