论文标题
大麻中核反应的神经网络
Neural Networks for Nuclear Reactions in MAESTROeX
论文作者
论文摘要
我们证明了使用神经网络来加速大师恒星流体动力学代码中的反应步骤。传统的大师模拟使用僵硬的颂歌积分器进行反应。在这里，我们采用重新系统体系结构并描述与网络的体系结构，培训和验证有关的详细信息。我们的定制方法包括损失功能形式的选项，表明使用平行神经网络会导致准确性提高，并描述在训练步骤中对模型鲁棒的扰动方法的描述。我们使用单步，3异位网络在毫米级火焰上测试我们的方法，该网络描述了IA型超新星型中发生的碳融合的第一阶段。我们使用来自标准Maestroex模拟的仿真数据训练神经网络，并证明可以有效地将所得模型应用于不同的火焰配置。这项工作为更复杂的网络和迭代的时间整合策略奠定了基础，可以利用神经网络的效率。
We demonstrate the use of neural networks to accelerate the reaction steps in the MAESTROeX stellar hydrodynamics code. A traditional MAESTROeX simulation uses a stiff ODE integrator for the reactions; here we employ a ResNet architecture and describe details relating to the architecture, training, and validation of our networks. Our customized approach includes options for the form of the loss functions, a demonstration that the use of parallel neural networks leads to increased accuracy, and a description of a perturbational approach in the training step that robustifies the model. We test our approach on millimeter-scale flames using a single-step, 3-isotope network describing the first stages of carbon fusion occurring in Type Ia supernovae. We train the neural networks using simulation data from a standard MAESTROeX simulation, and show that the resulting model can be effectively applied to different flame configurations. This work lays the groundwork for more complex networks, and iterative time-integration strategies that can leverage the efficiency of the neural networks.
