Articles | Volume 14, issue 5
Geosci. Model Dev., 14, 3067–3077, 2021
https://doi.org/10.5194/gmd-14-3067-2021
Geosci. Model Dev., 14, 3067–3077, 2021
https://doi.org/10.5194/gmd-14-3067-2021

Development and technical paper 28 May 2021

Development and technical paper | 28 May 2021

Physically regularized machine learning emulators of aerosol activation

Sam J. Silva et al.

Data sets

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

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 the representation of the more detailed physics and chemistry at a reduced computational cost while still retaining physical information.