Machine Learning Emulation of 3D Cloud Radiative Effects.

The treatment of cloud structure in numerical weather and climate models is often greatly simplified to make them computationally affordable. Here we propose to correct the European Centre for Medium‐Range Weather Forecasts 1D radiation scheme ecRad for 3D cloud effects using computationally cheap neural networks. 3D cloud effects are learned as the difference between ecRad's fast 1D Tripleclouds solver that neglects them and its 3D SPARTACUS (SPeedy Algorithm for Radiative TrAnsfer through CloUd Sides) solver that includes them but is about five times more computationally expensive. With typical errors between 20% and 30% of the 3D signal, neural networks improve Tripleclouds' accuracy for about 1% increase in runtime. Thus, rather than emulating the whole of SPARTACUS, we keep Tripleclouds unchanged for cloud‐free parts of the atmosphere and 3D‐correct it elsewhere. The focus on the comparably small 3D correction instead of the entire signal allows us to improve predictions significantly if we assume a similar signal‐to‐noise ratio for both. Plain Language Summary: Solar and terrestrial radiation is the primary driver of the Earth's weather and their detailed representation is essential for improving weather predictions and climate projections. Several aspects, however, such as the flow of radiation through the side of clouds and other three‐dimensional effects are often too costly to compute routinely. In this paper we describe how machine learning can help account for these effects cheaply. Key Points: Emulators are used to add 3D cloud effects to the fast 1D radiation solver Tripleclouds cheaplyEmulators are trained on 3D cloud effects from SPARTACUS, which is five times slower than TriplecloudsFor a 1% slowdown in Tripleclouds' runtime, 3D fluxes are emulated with an average error of about 20%–30% [ABSTRACT FROM AUTHOR]