Preprints
https://doi.org/10.5194/gmd-2020-393
https://doi.org/10.5194/gmd-2020-393

Submitted as: development and technical paper 21 Dec 2020

Submitted as: development and technical paper | 21 Dec 2020

Review status: a revised version of this preprint was accepted for the journal GMD.

Physically Regularized Machine Learning Emulators of Aerosol Activation

Sam J. Silva1, Po-Lun Ma1, Joseph C. Hardin1, and Daniel Rothenberg2 Sam J. Silva et al.
  • 1Pacific Northwest National Laboratory, Richland, WA
  • 2ClimaCell, Boston, MA

Abstract. The activation of aerosol into cloud droplets is an important step in the formation of clouds, and strongly influences the radiative budget of the Earth. Explicitly simulating aerosol activation in Earth system models is challenging due to the computational complexity required to resolve the necessary chemical and physical processes and their interactions. As such, various parameterizations have been developed to approximate these details at reduced computational cost and accuracy. Here, we explore how machine learning emulators can be used to bridge this gap in computational cost and parameterization accuracy. We evaluate a set of emulators of a detailed cloud parcel model using physically regularized machine learning regression techniques. We find that the emulators can reproduce the parcel model at higher accuracy than many existing parameterizations. Furthermore, physical regularization tends to improve emulator accuracy, most significantly when emulating very low activation fractions. This work demonstrates the value of physical constraints in machine learning model development and enables the implementation of improved hybrid physical-machine learning models of aerosol activation into next generation Earth system models.

Sam J. Silva et al.

 
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for authors/topical editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Sam J. Silva et al.

Data sets

Data for Silva et al. Activation Emulators Sam J. Silva https://doi.org/10.5281/zenodo.4319145

Sam J. Silva et al.

Viewed

Total article views: 468 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
363 103 2 468 2 5
  • HTML: 363
  • PDF: 103
  • XML: 2
  • Total: 468
  • BibTeX: 2
  • EndNote: 5
Views and downloads (calculated since 21 Dec 2020)
Cumulative views and downloads (calculated since 21 Dec 2020)

Viewed (geographical distribution)

Total article views: 414 (including HTML, PDF, and XML) Thereof 410 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Apr 2021
Download
Short summary
The activation of aerosol into cloud droplets is an important but uncertain process in the Earth system. The physical and chemical interactions that govern this process are too computationally expensive to explicitly resolve in modern Earth System Models. Here, we demonstrate how hybrid machine learning approaches can provide a potential path forward, enabling representation of the more detailed physics and chemistry at reduced computational cost while still retaining physical information.