用神经网络模拟宇宙气体动力学，加速星系形成建模。
Hybrid Physical-Neural Simulator for Fast Cosmological Hydrodynamics
- 引力用可微粒子网格法计算，流体动力学由神经网络建模压力场。
- 仅需一次参考模拟即可训练模型，数据效率高。
- 适合直接从观测数据拟合的下一代宇宙学研究。
宇宙场级推断需要可微分的前向模型，以求解气体与暗物质在流体动力学和引力作用下的复杂演化。我们提出一种混合方法：引力由可微粒子-网格求解器计算，而流体动力学则通过神经网络将局部物理量映射为有效压强场来建模。实验表明，该方法在场级和统计特征层面均优于基于焓梯度下降的基线方案。该方法具有极高数据效率，仅需一个宇宙结构形成的参考模拟即可约束神经压强模型，为未来直接基于观测数据训练模型打开了可能性。
原文摘要 · Abstract (English)
Cosmological field-level inference requires differentiable forward models that solve the challenging dynamics of gas and dark matter under hydrodynamics and gravity. We propose a hybrid approach where gravitational forces are computed using a differentiable particle-mesh solver, while the hydrodynamics are parametrized by a neural network that maps local quantities to an effective pressure field. We demonstrate that our method improves upon alternative approaches, such as an Enthalpy Gradient Descent baseline, both at the field and summary-statistic level. The approach is furthermore highly data efficient, with a single reference simulation of cosmological structure formation being sufficient to constrain the neural pressure model. This opens the door for future applications where the model is fit directly to observational data, rather than a training set of simulations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。