论文标题
快速N体模拟的混合物理神经ODE
Hybrid Physical-Neural ODEs for Fast N-body Simulations
论文作者
论文摘要
我们提出了一种新的方案，以补偿粒子网（PM）方案产生的小规模近似值，以进行宇宙N体模拟。这种模拟是大规模结构的快速和低计算成本实现，但缺乏小规模的分辨率。为了提高其准确性，我们在模拟的微分方程中引入了额外的有效力，该方程是由作用于PM估计的引力电位的傅立叶空间神经网络参数化的。我们将获得功率谱的结果与PGD方案（潜在梯度下降方案）获得的结果进行了比较。我们注意到功率光谱期限有类似的改进，但是我们发现我们的方法在互相关系数方面的表现优于PGD，并且对模拟设置的变化（不同的分辨率，不同的宇宙学）的变化更为强大。
We present a new scheme to compensate for the small-scales approximations resulting from Particle-Mesh (PM) schemes for cosmological N-body simulations. This kind of simulations are fast and low computational cost realizations of the large scale structures, but lack resolution on small scales. To improve their accuracy, we introduce an additional effective force within the differential equations of the simulation, parameterized by a Fourier-space Neural Network acting on the PM-estimated gravitational potential. We compare the results for the matter power spectrum obtained to the ones obtained by the PGD scheme (Potential gradient descent scheme). We notice a similar improvement in term of power spectrum, but we find that our approach outperforms PGD for the cross-correlation coefficients, and is more robust to changes in simulation settings (different resolutions, different cosmologies).
