基于物理信息神经网络的微分恒星大气模型
Differentiable Stellar Atmospheres with Physics-Informed Neural Networks
AI总结:
本文提出物理信息神经网络Kurucz-a1,模拟LTE下的一维恒星大气,通过流体静力学约束实现可微求解,优于ATLAS-12,支持数据驱动的恒星参数优化。
摘要:
我们提出了Kurucz-a1,一种物理信息神经网络(PINN),用于模拟局部热平衡(LTE)条件下的一维恒星大气模型,解决了微分恒星光谱学中的一个关键瓶颈。通过在训练过程中将流体静力学平衡作为物理约束,Kurucz-a1创建了一个可微的大气结构求解器,在保持物理一致性的同时实现了计算效率。Kurucz-a1能够实现优于ATLAS-12本身的流体静力学平衡,并且与太阳观测光谱更加一致,展示了现代优化技术的优势。结合现代可微辐射传输代码,该方法能够实现对不同恒星群体中通用物理参数的数据驱动优化——这是下一代恒星天体物理学所必需的能力。
英文摘要:
We present Kurucz-a1, a physics-informed neural network (PINN) that emulates 1D stellar atmosphere models under Local Thermodynamic Equilibrium (LTE), addressing a critical bottleneck in differentiable stellar spectroscopy. By incorporating hydrostatic equilibrium as a physical constraint during training, Kurucz-a1 creates a differentiable atmospheric structure solver that maintains physical consistency while achieving computational efficiency. Kurucz-a1 can achieve superior hydrostatic equilibrium and more consistent with the solar observed spectra compared to ATLAS-12 itself, demonstrating the advantages of modern optimization techniques. Combined with modern differentiable radiative transfer codes, this approach enables data-driven optimization of universal physical parameters across diverse stellar populations-a capability essential for next-generation stellar astrophysics.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。