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

• URL: http://arxiv.org/abs/2510.27050v1
• Date: Thu, 30 Oct 2025 23:38:53 GMT
• Title: Accelerating Radiative Transfer for Planetary Atmospheres by Orders of Magnitude with a Transformer-Based Machine Learning Model
• Authors: Isaac Malsky, Tiffany Kataria, Natasha E. Batalha, Matthew Graham,
• Abstract summary: Emulating radiative transfer with machine learning opens up the possibility for faster and more accurate routines within planetary atmospheric models.<n>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.
• Score: 0.0044302156879028705
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Machine learning based radiative parameterization scheme and its performance in operational reforecast experiments [21.24990493675443]
  This study investigates limitations inherent to hybrid forecasting frameworks that embed deep neural networks into numerical prediction models.<n>A residual convolutional neural network is employed to approximate the Rapidive Transfer Model for General Circulation Models (RRTMG) within the global operational system of China Meteorological Administration.<n>A LibTorch-based coupling method is utilized, which is more suitable for real-time operational computations.
  arXiv  Detail & Related papers  (2026-01-20T04:45:45Z)
• Inverse Autoregressive Flows for Zero Degree Calorimeter fast simulation [0.0]
  Physics-based machine learning blends traditional science with modern data-driven techniques.<n>We leverage this paradigm to accelerate simulations of the Zero Degree Calorimeter (ZDC) of the ALICE experiment at CERN.<n>Our approach not only outperforms classic data-driven model assimilation but also yields models that are 421 times faster than existing NF implementations in ZDC simulation literature.
  arXiv  Detail & Related papers  (2025-12-23T13:28:15Z)
• A First Full Physics Benchmark for Highly Granular Calorimeter Surrogates [0.0]
  This work studies the use of highly granular generative calorimeter surrogates in a realistic simulation application.<n>We introduce DDML, a generic library which enables the combination of generative calorimeter surrogates with realistic detectors.<n>We compare two different generative models - one operating on a regular grid representation, and the other using a less common point cloud approach.
  arXiv  Detail & Related papers  (2025-11-21T15:06:49Z)
• Fusing CFD and measurement data using transfer learning [49.1574468325115]
  We introduce a non-linear method based on neural networks combining simulation and measurement data via transfer learning.<n>In a first step, the neural network is trained on simulation data to learn spatial features of the distributed quantities.<n>The second step involves transfer learning on the measurement data to correct for systematic errors between simulation and measurement by only re-training a small subset of the entire neural network model.
  arXiv  Detail & Related papers  (2025-07-28T07:21:46Z)
• FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling [10.780042503723806]
  FuXi-RTM is a physics-guided deep learning framework designed to enhance weather forecast accuracy while enforcing physical consistency.<n>FuXi-RTM integrates a primary forecasting model (FuXi) with a fixed deep learning-based radiative transfer model (DLRTM) surrogate.<n> evaluated over a 5-year dataset, FuXi-RTM outperforms its unconstrained counterpart in 88.51% of 3320 variable and lead time combinations.
  arXiv  Detail & Related papers  (2025-03-25T08:21:58Z)
• Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
  We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks. We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks. In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
  arXiv  Detail & Related papers  (2024-06-21T13:48:37Z)
• Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research [76.93956925360638]
  Waymax is a new data-driven simulator for autonomous driving in multi-agent scenes. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training. We benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions.
  arXiv  Detail & Related papers  (2023-10-12T20:49:15Z)
• Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN [8.980453507536017]
  Currently, over half of the computing power at CERN GRID is used to run High Energy Physics simulations. The recent updates at the Large Hadron Collider (LHC) create the need for developing more efficient simulation methods. We propose an alternative approach to the problem that leverages machine learning.
  arXiv  Detail & Related papers  (2023-06-23T16:45:46Z)
• High-precision interpolation of stellar atmospheres with a deep neural network using a 1D convolutional auto encoder for feature extraction [0.0]
  We establish a reliable, precise, lightweight, and fast method for recovering stellar model atmospheres. We employ a fully connected deep neural network which in turn uses a 1D convolutional auto-encoder to extract the nonlinearities of a grid. We show a higher precision with a convolutional auto-encoder than using principal component analysis as a feature extractor.
  arXiv  Detail & Related papers  (2023-06-12T08:16:26Z)
• Continual learning autoencoder training for a particle-in-cell simulation via streaming [52.77024349608834]
  upcoming exascale era will provide a new generation of physics simulations with high resolution. These simulations will have a high resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible. This work presents an approach that trains a neural network concurrently to a running simulation without data on a disk.
  arXiv  Detail & Related papers  (2022-11-09T09:55:14Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Learning the Physics of Particle Transport via Transformers [0.0]
  We present a data-driven dose calculation algorithm predicting the dose deposited by mono-energetic proton beams. Our proposed model is 33 times faster than current clinical analytic pencil beam algorithms. Our model could overcome a major obstacle that has so far prohibited real-time adaptive proton treatments.
  arXiv  Detail & Related papers  (2021-09-08T22:26:03Z)
• Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transfer [56.34005280792013]
  We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number. We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
  arXiv  Detail & Related papers  (2021-01-19T16:14:02Z)
• Predicting atmospheric optical properties for radiative transfer computations using neural networks [0.0]
  We develop a machine learning-based parametrization for the gaseous optical properties by training neural networks to emulate a modern radiation parameterization (RRTMGP) Our neural network-based gas optics parametrization is up to 4 times faster than RRTMGP, depending on the size of the neural networks. We conclude that our machine learning-based parametrization can speed-up radiative transfer computations whilst retaining high accuracy.
  arXiv  Detail & Related papers  (2020-05-05T15:00:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.