Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization

Abstract

Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1-6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear-sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line-by-line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top-of-atmosphere radiative forcings typically below 0.1 K day −1 and 0.5 W m −2 , respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy. Plain Language Summary Solar and terrestrial radiation interact with Earth's atmosphere, surface, and clouds and provide the energy which drives climate and weather. Simulating these radiative flows in climate and weather models is crucial and can also be very time-consuming. One possible way to model radiative effects more efficiently is to use neural networks or similar machine learning algorithms, but predictions are not guaranteed to be realistic because such models do not use physical equations. Here we investigate using neural networks to replace only one part of traditional radiation code, where the optical properties of the atmosphere are computed. We have found that this approach can be several times faster, while still being accurate in various situations, such as simulating future climate.

Machine Learning Emulation of Gravity Wave Drag in Numerical Weather Forecasting

“…Veerman and Pincus (2021) emulate a radiation scheme and assess the computational cost relative to the existing scheme. Ukkonen et al (2020) emulate the gas optics scheme…”

“…Ukkonen et al. ( 2020 ) emulate the gas optics scheme within a radiation scheme, providing acceleration for this kernel. Gettelman et al.…”

“…Veerman and Pincus (2021) emulate a radiation scheme and assess the computational cost relative to the existing scheme. Ukkonen et al (2020) emulate the gas optics scheme within a radiation scheme, providing acceleration for this kernel. Gettelman et al (2020) use a NN to learn an increased complexity microphysics model and reduce the cost down to that of their reference scheme.…”

Improved Weather Forecasting Using Neural Network Emulation for Radiation Parameterization

“…The radiative transfer for TOVS (RTTOV) has been developed using multiple linear regression since 1999, and it has been widely used in data assimilation in the NWP model (Saunders et al, 2018). Recent studies on radiative transfer modeling have extended the application of various AI techniques, including multiple linear regression, deep neural network (DNN), adaptive network-based fuzzy inference system, and convolutional neural network (CNN) for radiation processes over a clear sky (Bilgic & Mert, 2021;Liu et al, 2020;Ukkonen et al, 2020;Veerman et al, 2021) and 3-dimensional cloud radiative effects (Meyer et al, 2021). As these studies do not utilize repetition by time integration, such as in the numerical forecast model, errors caused by emulation do not accumulate.…”

Machine Learning Emulation of 3D Cloud Radiative Effects

“…As an alternative method to the emulation of an entire radiation scheme, Ukkonen et al. (2020) and Veerman et al. (2021) show a different approach whereby specific parts of a scheme, such as the gas optics in the RTE‐RRTMGP (Radiative Transfer for Energetics and Rapid and accurate Radiative Transfer Model for General circulation models applications‐Parallel; Pincus et al., 2019) framework, are emulated, retaining the original radiative transfer solver.…”