CASI: A Convolutional Neural Network Approach for Shell Identification
CASI: A Convolutional Neural Network Approach for Shell Identification
复制标题
DOI：
10.3847/1538-4357/ab275e
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Colin M. Van Oort;Duo Xu;S. Offner;R. Gutermuth
中科院分区：
文献类型：
--
作者：
Colin M. Van Oort;Duo Xu;S. Offner;R. Gutermuth
我们利用深度学习技术来识别模拟分子云中的恒星反馈特征。具体来说，我们实现了一个具有类似于U-Net架构的深度神经网络，并将其应用于使用嵌入恒星源的湍流分子云的磁流体动力学模拟数据识别风驱动的壳和气泡的问题。该网络适用于两个任务，密集回归和分割，两种数据，模拟密度和合成12 CO观测。我们的壳识别卷积方法（casi）能够在两个分割任务中获得大于90%的真阳性率，同时保持1%的假阳性率，并且在相关回归任务中表现良好。casi的源代码可在GitLab上获得。
We utilize techniques from deep learning to identify signatures of stellar feedback in simulated molecular clouds. Specifically, we implement a deep neural network with an architecture similar to U-Net and apply it to the problem of identifying wind-driven shells and bubbles using data from magnetohydrodynamic simulations of turbulent molecular clouds with embedded stellar sources. The network is applied to two tasks, dense regression and segmentation, on two varieties of data, simulated density and synthetic 12CO observations. Our Convolutional Approach for Shell Identification (casi) is able to obtain a true-positive rate greater than 90%, while maintaining a false-positive rate of 1%, on two segmentation tasks and also performs well on related regression tasks. The source code for casi is available on GitLab.