Application of Convolutional Neural Networks to Identify Protostellar Outflows in CO Emission
Application of Convolutional Neural Networks to Identify Protostellar Outflows in CO Emission
复制标题
DOI：
10.3847/1538-4357/abc7bf
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Duo Xu;S. Offner;R. Gutermuth;C. V. Oort
中科院分区：
文献类型：
--
作者：
Duo Xu;S. Offner;R. Gutermuth;C. V. Oort
我们采用深度学习方法casi-3d（卷积方法结构识别-3D）来识别分子线光谱中的原恒星流出。我们进行磁流体动力学模拟，模拟发射原恒星外流的形成恒星，并使用这些来生成合成观测。我们应用三维辐射传输程序radmc-3d模拟了模拟云的12 CO（J = 1-0）谱线发射。我们训练了两个casi-3d模型：ME 1被训练为仅预测流出物的位置，而MF被训练为预测来自每个体素中流出物的质量分数。这两个模型成功地识别了所有60个先前在英仙座视觉上识别出的外流。此外，casi-3d发现了20个新的高信心资金外流。所有这些都有相干的高速结构，其中17个附近有年轻的恒星物体，而其余3个则在斯皮策巡天覆盖范围之外。MF模型预测的英仙座单个外流的质量、动量和能量与以前的估计相当。这种相似性是由于误差的抵消：以前的计算错过了速度与云速度相当的流出物质;然而，他们通过高估具有非流出气体污染的较高速度下的质量来补偿这一点。我们发现，流出可能驱动的较老的来源有更多的高速气体相比，年轻的来源。
We adopt the deep learning method casi-3d (Convolutional Approach to Structure Identification-3D) to identify protostellar outflows in molecular line spectra. We conduct magnetohydrodynamics simulations that model forming stars that launch protostellar outflows and use these to generate synthetic observations. We apply the 3D radiation transfer code radmc-3d to model 12CO (J = 1–0) line emission from the simulated clouds. We train two casi-3d models: ME1 is trained to predict only the position of outflows, while MF is trained to predict the fraction of the mass coming from outflows in each voxel. The two models successfully identify all 60 previously visually identified outflows in Perseus. Additionally, casi-3d finds 20 new high-confidence outflows. All of these have coherent high-velocity structure, and 17 of them have nearby young stellar objects, while the remaining three are outside the Spitzer survey coverage. The mass, momentum, and energy of individual outflows in Perseus predicted by model MF is comparable to the previous estimations. This similarity is due to a cancellation in errors: previous calculations missed outflow material with velocities comparable to the cloud velocity; however, they compensate for this by overestimating the amount of mass at higher velocities that has contamination from nonoutflow gas. We show that outflows likely driven by older sources have more high-velocity gas compared to those driven by younger sources.