Cleaning our own dust: simulating and separating galactic dust foregrounds with neural networks
Cleaning our own dust: simulating and separating galactic dust foregrounds with neural networks
复制标题
DOI：
10.1093/mnras/staa3344
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
K. Aylor;M. Haq;L. Knox;Y. Hezaveh;L. Perreault-Levasseur
中科院分区：
文献类型：
--
作者：
K. Aylor;M. Haq;L. Knox;Y. Hezaveh;L. Perreault-Levasseur
从宇宙微波背景辐射（CMB）图中分离银河前景辐射，并量化由于前景分离误差而导致的CMB图中的不确定性，对于避免科学结论中的偏差非常重要。我们量化这种不确定性的能力是有限的，我们缺乏一个模型的前景排放的统计分布。在这里，我们使用深度卷积生成对抗网络（DCGAN）来创建星际尘埃发射强度的有效非高斯统计模型。对于训练数据，我们使用一组从普朗克卫星的观测中推断出的尘埃图。DCGAN特别适合于这种无监督学习任务，因为它可以直接从示例中学习对复杂的非高斯分布建模。然后，我们使用这些模拟来训练第二个神经网络，以从灰尘污染的地图中估计潜在的CMB信号。我们讨论了其他潜在的用途训练DCGAN，和泛化到偏振发射尘埃和同步加速器。
Separating galactic foreground emission from maps of the cosmic microwave background (CMB), and quantifying the uncertainty in the CMB maps due to errors in foreground separation are important for avoiding biases in scientific conclusions. Our ability to quantify such uncertainty is limited by our lack of a model for the statistical distribution of the foreground emission. Here we use a Deep Convolutional Generative Adversarial Network (DCGAN) to create an effective non-Gaussian statistical model for intensity of emission by interstellar dust. For training data we use a set of dust maps inferred from observations by the Planck satellite. A DCGAN is uniquely suited for such unsupervised learning tasks as it can learn to model a complex non-Gaussian distribution directly from examples. We then use these simulations to train a second neural network to estimate the underlying CMB signal from dust-contaminated maps. We discuss other potential uses for the trained DCGAN, and the generalization to polarized emission from both dust and synchrotron.