Assessing the Performance of a Machine Learning Algorithm in Identifying Bubbles in Dust Emission
Assessing the Performance of a Machine Learning Algorithm in Identifying Bubbles in Dust Emission
复制标题
评估机器学习算法在识别粉尘排放中的气泡方面的性能
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
S. Offner
中科院分区：
文献类型：
--
作者：
Duo 铎 Xu 许;S. Offner
由大质量恒星的辐射和风产生的恒星反馈在分子云的物理和化学演化中起着重要作用。这种能量和动量会留下一个可识别的信号（“气泡”），影响云的动力学和结构。大多数气泡搜索都是“通过眼睛”执行的，这通常是耗时的，主观的，并且难以校准。基于机器学习的自动分类使得对气泡进行系统的、可量化的和可重复的搜索成为可能。我们采用了以前开发的机器学习算法，Brut，并定量评估其性能，在识别气泡使用合成粉尘观测。我们采用磁流体动力学模拟，该模拟恒星风在湍流分子云内发射，作为生成合成图像的输入。我们使用一个公开可用的三维尘埃连续蒙特卡罗辐射传输代码，hypap，在三个斯皮策波段（4.5，8和24 μm）生成气泡的合成图像。我们指定一半的合成气泡作为训练集，我们用它来训练布鲁特沿着来自银河系项目（MWP）的公民科学数据。然后，我们评估布鲁特的准确性使用剩余的合成观测。我们发现，Brut的表现后，再培训显着增加，它能够识别黄色的气泡，这可能是与B型恒星。Brut继续在先前识别的高分气泡上表现良好，并且超过10%的MWP气泡被重新分类为高置信度气泡，其先前在MWP数据中是边缘或模糊的检测。我们还研究了训练集的大小，灰尘模型，进化阶段和背景噪声对气泡识别的影响。
Stellar feedback created by radiation and winds from massive stars plays a significant role in both physical and chemical evolution of molecular clouds. This energy and momentum leaves an identifiable signature (“bubbles”) that affects the dynamics and structure of the cloud. Most bubble searches are performed “by eye,” which is usually time-consuming, subjective, and difficult to calibrate. Automatic classifications based on machine learning make it possible to perform systematic, quantifiable, and repeatable searches for bubbles. We employ a previously developed machine learning algorithm, Brut, and quantitatively evaluate its performance in identifying bubbles using synthetic dust observations. We adopt magnetohydrodynamics simulations, which model stellar winds launching within turbulent molecular clouds, as an input to generate synthetic images. We use a publicly available three-dimensional dust continuum Monte Carlo radiative transfer code, hyperion, to generate synthetic images of bubbles in three Spitzer bands (4.5, 8, and 24 μm). We designate half of our synthetic bubbles as a training set, which we use to train Brut along with citizen-science data from the Milky Way Project (MWP). We then assess Brut’s accuracy using the remaining synthetic observations. We find that Brut’s performance after retraining increases significantly, and it is able to identify yellow bubbles, which are likely associated with B-type stars. Brut continues to perform well on previously identified high-score bubbles, and over 10% of the MWP bubbles are reclassified as high-confidence bubbles, which were previously marginal or ambiguous detections in the MWP data. We also investigate the influence of the size of the training set, dust model, evolutionary stage, and background noise on bubble identification.
大质量星团中的大质量恒星 - IV 动量驱动风对云层的破坏
影响因子：
4.8
作者：
Ngoumou;Ercolano;Bonnell
通讯作者：
Bonnell