论文标题
在自动编码器和替代模型中的高保真不透明度光谱的转移学习
Transfer Learning of High-Fidelity Opacity Spectra in Autoencoders and Surrogate Models
论文作者
论文摘要
高能密度物理学的仿真很昂贵，部分原因是需要产生非本地热力学平衡的不透明性。高保真光谱可能会揭示出在低保真光谱未看到的模拟中的新物理，但是这些模拟的成本也随着所使用的不透明性的忠诚度而扩展。神经网络能够重现这些光谱，但是神经网络需要数据来训练它们，从而限制了训练数据的忠诚度。本文表明，可以在3 \％至4 \％的领域中使用中位数误差的高保真光谱，使用少于50个高保真k KI的数据样本，通过对经过多次培训的神经网络进行转移学习，以多倍的低缺失数据进行转移。
Simulations of high energy density physics are expensive, largely in part for the need to produce non-local thermodynamic equilibrium opacities. High-fidelity spectra may reveal new physics in the simulations not seen with low-fidelity spectra, but the cost of these simulations also scale with the level of fidelity of the opacities being used. Neural networks are capable of reproducing these spectra, but neural networks need data to to train them which limits the level of fidelity of the training data. This paper demonstrates that it is possible to reproduce high-fidelity spectra with median errors in the realm of 3\% to 4\% using as few as 50 samples of high-fidelity Krypton data by performing transfer learning on a neural network trained on many times more low-fidelity data.
