Accelerating Radiative Transfer for Planetary Atmospheres by Orders of Magnitude with a Transformer-Based Machine Learning Model

TL;DR

This paper introduces a transformer-based machine learning model that significantly accelerates radiative transfer calculations in planetary atmospheres, achieving 100x speedup with high accuracy, thus enabling more efficient atmospheric modeling.

Contribution

The paper presents a novel encoder-only transformer neural network that emulates radiative transfer calculations with high accuracy and speed, surpassing traditional methods.

Findings

Achieved ~1% error in flux predictions compared to traditional methods.

Realized 100x speedup in radiative transfer calculations.

Demonstrated potential for integration into planetary atmospheric models.

Abstract

Radiative transfer calculations are essential for modeling planetary atmospheres. However, standard methods are computationally demanding and impose accuracy-speed trade-offs. High computational costs force numerical simplifications in large models (e.g., General Circulation Models) that degrade the accuracy of the simulation. Radiative transfer calculations are an ideal candidate for machine learning emulation: fundamentally, it is a well-defined physical mapping from a static atmospheric profile to the resulting fluxes, and high-fidelity training data can be created from first principles calculations. We developed a radiative transfer emulator using an encoder-only transformer neural network architecture, trained on 1D profiles representative of solar-composition hot Jupiter atmospheres. Our emulator reproduced bolometric two-stream layer fluxes with mean test set errors of ~1% compared to the traditional method and achieved speedups of 100x. Emulating radiative transfer with machine learning opens up the possibility for faster and more accurate routines within planetary atmospheric models such as GCMs.