Essential Maintenance: All Authorea-powered sites will be offline 9am-10am EDT Tuesday 28 May
and 11pm-1am EDT Tuesday 28-Wednesday 29 May. We apologise for any inconvenience.

loading page

Revisiting Machine Learning Approaches for Short- and Longwave Radiation Inference in Weather and Climate Models, Part I: Offline Performance
  • +1
  • Guillaume Bertoli,
  • Firat Ozdemir,
  • Sebastian Schemm,
  • Fernando Perez-Cruz
Guillaume Bertoli
ETHZ

Corresponding Author:[email protected]

Author Profile
Firat Ozdemir
ETH Zurich
Author Profile
Sebastian Schemm
ETH Zurich
Author Profile
Fernando Perez-Cruz
Swiss Data Science Center, ETH Zurich
Author Profile

Abstract

As climate modellers prepare their code for kilometre-scale global simulations, the computationally demanding radiative transfer parameterization is a prime candidate for machine learning (ML) emulation. Because of the computational demands, many weather centres use a reduced spatial grid and reduced temporal frequency for radiative transfer calculations in their forecast models. This strategy is known to affect forecast quality, which further motivates the use of ML-based radiative transfer parameterizations. This paper contributes to the discussion on how to incorporate physical constraints into an ML-based radiative parameterization, and how different neural network (NN) designs and output normalisation affect prediction performance. A random forest (RF) is used as a baseline method, with the European Centre for Medium-Range Weather Forecasts (ECMWF) model ecRad, the operational radiation scheme in the Icosahedral Nonhydrostatic Weather and Climate Model (ICON), used for training. Surprisingly, the RF is not affected by the top-of-atmosphere (TOA) bias found in all NNs tested (e.g., MLP, CNN, UNet, RNN) in this and previously published studies. At lower atmospheric levels, the RF can compete with all NNs tested, but its memory requirements quickly become prohibitive. For a fixed memory size, most NNs outperform the RF except at TOA. The most accurate emulator is a recurrent neural network architecture that closely imitates the physical process it emulates. The shortwave and longwave fluxes are normalized to reduce their dependence on the solar angle and surface temperature respectively. The model are, furthermore, trained with an additional heating rates penalty in the loss function.
29 Mar 2024Submitted to ESS Open Archive
29 Mar 2024Published in ESS Open Archive