发表机构
UC Santa Cruz（加州大学圣克鲁兹分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有火星GCM不可微分且难以标定的问题，提出模块化可微分火星气候模型AEGIS，耦合Dinosaur动力核心并支持神经闭合，实现稳定十年模拟，再现二氧化碳循环和表面温度，且梯度可支持物理标定与神经训练。
AI 中文摘要
大气环流模型（GCM）是模拟行星大气的主要工具。它们在理解火星大气方面发挥着至关重要的作用，因为预测其独特的天气对于进入、下降和着陆等操作任务至关重要。火星对这些模型提出了不寻常的挑战，因为与地球相比，其观测数据稀疏。此外，稀薄的二氧化碳大气与辐射活跃的尘埃循环相结合，形成了具有较大昼夜温度波动的易变大气，且没有真正的地球类似物可供验证。现有的火星GCM，包括LMD PCM、NASA Ames火星GCM和PlanetWRF，虽然成熟且物理细节丰富，但均以传统Fortran语言实现，采用有限差分或有限体积求解器，且不提供梯度用于标定或机器学习。在此，我们提出AEGIS，一个模块化的可微分火星气候模型，它将火星独特的大气物理与Dinosaur动力学核心耦合，并提供神经闭合的接口。我们展示了稳定的十年火星模拟，这些模拟再现了季节性二氧化碳循环，同时保持总二氧化碳储量守恒，捕捉了真实的大尺度表面温度结构，并产生了遵循火星轨道器激光高度计（MOLA）地形的表面压力。通过耦合轨迹的梯度与有限差分一致，并支持物理标定和神经训练。我们与传统GCM进行比较，突出了该框架的计算效率和可微分性。
英文摘要
General circulation models (GCMs) are the primary tool for simulating planetary atmospheres. They play a vital role in understanding Mars's atmosphere, as forecasting its unique weather is mission-critical for operations such as entry, descent, and landing. Mars poses unusual challenges for these models, as observations are sparse compared to Earth. In addition, a thin \co{} atmosphere alongside a radiatively active dust cycle creates a volatile atmosphere with large diurnal temperature swings and no true terrestrial analog for validation. Existing Mars GCMs, including the LMD PCM, the NASA Ames Mars GCM, and PlanetWRF, are mature and physically detailed but are implemented in legacy Fortran with finite-difference or finite-volume solvers, and they do not expose gradients for calibration or machine learning. Here we present AEGIS, a modular differentiable Mars climate model that couples Mars's unique atmospheric physics to the Dinosaur dynamical core, with interfaces for neural closures. We showcase stable ten-Mars-year simulations that reproduce the seasonal \co{} cycle while conserving the total \co{} inventory, capture realistic large-scale surface-temperature structure, and produce surface pressure that follows Mars Orbiter Laser Altimeter (MOLA) topography. Gradients through coupled trajectories agree with finite differences and support physical calibration and neural training. We compare with conventional GCMs, highlighting the framework's computational efficiency and differentiability.
