发表机构
Jet Propulsion Laboratory, California Institute of Technology; University of California Santa Cruz; California Institute of Technology; Georgia Institute of Technology; NVIDIA Corporation; University of California, Riverside; Institute of Astronomy and Astrophysics, Academia Sinica; University of Bern（加州理工学院喷气推进实验室; 加州大学圣克鲁兹分校; 加州理工学院; 佐治亚理工学院; 英伟达公司; 加州大学河滨分校; 中央研究院天文及天文物理研究所; 伯尔尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于残差流图架构的机器学习局部框化学动力学求解器，实现系外行星大气模拟的微秒级推理，精度达百分级，速度远超经典求解器，可覆盖宽参数空间，性能优于常用机器学习架构。
AI 中文摘要
观测越来越多地揭示了塑造系外行星大气的辐射、化学和动力学耦合过程，解释这些大气需要能捕捉这种复杂性的模型，但多维模型根本上受限于计算成本，回答关键问题需要以经典方法无法达到的速度模拟主导物理机制，因此模型常依赖平衡化学等简化近似，即便这些假设会遗漏重要效应，故亟需快速且准确的化学动力学求解器来模拟行星大气。本文提出一种用于系外行星大气的机器学习局部框化学动力学求解器，采用残差流图架构，证明该替代模型比经典求解器快几个数量级，实现微秒级推理，同时保持百分级精度，其覆盖的参数空间范围为：温度T=300-3000 K，压力P=10⁻⁶-10⁴ bar，时间步长Δt=10⁻³-10⁸ s，以及C/O比和金属丰度为太阳的10⁻²到10³倍的成分；该模型优于几种常用机器学习架构，在大气化学特有的极端刚性条件下表现稳健，本文提出的机器学习框架是模拟数值模拟中常见的态到态流图问题的灵活高效方法。
英文摘要
Observations increasingly reveal the coupled radiative, chemical, and dynamical processes that shape exoplanet atmospheres. Interpreting these atmospheres requires models that can capture this complexity. However, multidimensional models remain fundamentally limited by computational cost, and answering key questions requires simulating the governing physical mechanisms at speeds classical methods cannot achieve. As a result, models often rely on simplifying approximations, such as equilibrium chemistry, even when those assumptions miss important effects. There is a pressing need for fast and accurate chemical kinetics solvers to model planetary atmospheres. Here we present a machine learning local-box chemical kinetics solver for exoplanet atmospheres using a residual flow-map architecture. We demonstrate that this surrogate model is several orders of magnitude faster than a classical solver, achieving microsecond-scale inference while retaining percent-level accuracy. The surrogate model covers a parameter space that spans $T=300$-$3000$ K, $P=10^{-6}$-$10^{4}$ bar, $Δt=10^{-3}$-$10^{8}$ s, and compositions ranging from $10^{-2}$ to $10^{3}$ times solar in both C/O ratio and metallicity. Our model outperforms several commonly used machine learning architectures and performs robustly under the extreme stiffness characteristic of atmospheric chemistry. The machine learning framework presented here is a flexible and efficient approach to emulating state-to-state flow-map problems that commonly arise in numerical simulations.
Comments15 pages, 7 figures. Accepted for publication in ApJ
