Emulating radiative transfer with artificial neural networks
Emulating radiative transfer with artificial neural networks
复制标题
使用人工神经网络模拟辐射传输
DOI：
10.1093/mnras/stad2524
复制
发表时间：
2023
影响因子：
4.8
通讯作者：
Wise, John H.
中科院分区：
文献类型：
--
作者：
Sethuram, Snigdaa S.;Cochrane, Rachel K.;Hayward, Christopher C.;Acquaviva, Viviana;Villaescusa-Navarro, Francisco;Popping, Gergö;Wise, John H.
来自星系模拟的正演模拟观测数据使得理论和观测之间的直接比较成为可能。为了生成包括尘埃吸收、再发射和散射在内的合成光谱能量分布(SED)，蒙特卡罗辐射转移通常用于逐个星系的后处理。然而，这在计算上是昂贵的，特别是如果一个人想要对许多宇宙学模拟的套件进行预测。为了减轻这一计算负担，我们开发了一个使用人工神经网络(ANN)ANNglina的辐射传输模拟器，它可以使用模拟星系的少量综合属性来可靠地预测模拟星系的SED：恒星形成率、恒星和尘埃质量，以及所有恒星粒子和只有年龄为10岁的恒星粒子的质量加权金属含量。在这里，我们介绍了方法，并量化了预测的准确性。我们用插图TNG项目的TNG50宇宙磁流体动力学模拟计算的星系的SED来训练ANN，ANN能够预测TNG50星系在紫外线(UV)到毫米范围内的SED，典型的绝对误差中值为∼7% %。在紫外区预测误差最大，这可能是由于在该波长范围内视角依赖性最大所致。我们的结果表明，我们的基于人工神经网络的模拟器是一种很有前途的计算廉价的替代方案，用于从宇宙学模拟中对星系SED进行正演模拟。
Forward-modeling observables from galaxy simulations enables direct comparisons between theory and observations. To generate synthetic spectral energy distributions (SEDs) that include dust absorption, re-emission, and scattering, Monte Carlo radiative transfer is often used in post-processing on a galaxy-by-galaxy basis. However, this is computationally expensive, especially if one wants to make predictions for suites of many cosmological simulations. To alleviate this computational burden, we have developed a radiative transfer emulator using an artificial neural network (ANN),ANNgelina, that can reliably predict SEDs of simulated galaxies using a small number of integrated properties of the simulated galaxies: star formation rate, stellar and dust masses, and mass-weighted metallicities of all star particles and of only star particles with age <10 Myr. Here, we present the methodology and quantify the accuracy of the predictions. We train the ANN on SEDs computed for galaxies from theIllustrisTNGproject’s TNG50 cosmological magnetohydrodynamical simulation.ANNgelinais able to predict the SEDs of TNG50 galaxies in the ultraviolet (UV) to millimetre regime with a typical median absolute error of ∼7 per cent. The prediction error is the greatest in the UV, possibly due to the viewing-angle dependence being greatest in this wavelength regime. Our results demonstrate that our ANN-based emulator is a promising computationally inexpensive alternative for forward-modeling galaxy SEDs from cosmological simulations.