Machine Learning Emulation of 3D Cloud Radiative Effects
This work addresses the computational bottleneck in numerical weather and climate modeling for meteorologists and climate scientists, offering an incremental improvement by focusing on correcting 3D effects rather than emulating the entire expensive solver.
The authors tackled the computational cost of including 3D cloud radiative effects in weather models by using neural networks to correct a fast 1D solver, achieving typical errors of 20-30% of the 3D signal with only a 1% runtime increase.
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.