Data-driven Reconstruction of Gravitationally Lensed Galaxies Using Recurrent Inference Machines
Data-driven Reconstruction of Gravitationally Lensed Galaxies Using Recurrent Inference Machines
复制标题
DOI：
10.3847/1538-4357/ab35d7
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
W. Morningstar;Laurence Perreault Levasseur;Y. Hezaveh;R. Blandford;P. Marshall;P. Putzky;T. D. Rueter;R. Wechsler;M. Welling
中科院分区：
文献类型：
--
作者：
W. Morningstar;Laurence Perreault Levasseur;Y. Hezaveh;R. Blandford;P. Marshall;P. Putzky;T. D. Rueter;R. Wechsler;M. Welling
我们提出了一种机器学习方法，用于重建强透镜系统中背景源的未失真图像。该方法将源视为像素化图像，并利用循环推理机迭代地重建给定镜头模型的背景源。我们的架构学习使用物理前向模型（光线追踪模拟）在给定数据的情况下最大化模型参数（源像素）的可能性，同时从训练数据中隐式学习源结构的先验。与线性反演方法相比，这会带来更好的性能，其中先验信息仅限于用高斯形式近似的源像素的两点协方差，并且通常以相对任意的方式指定。我们将源重建网络与卷积神经网络相结合，直接根据望远镜图像预测透镜星系中质量分布的参数，从而实现背景源图像和前景质量分布的全自动重建。
We present a machine-learning method for the reconstruction of the undistorted images of background sources in strongly lensed systems. This method treats the source as a pixelated image and utilizes the recurrent inference machine to iteratively reconstruct the background source given a lens model. Our architecture learns to maximize the likelihood of the model parameters (source pixels) given the data using the physical forward model (ray-tracing simulations) while implicitly learning the prior of the source structure from the training data. This results in better performance compared to linear inversion methods, where the prior information is limited to the two-point covariance of the source pixels approximated with a Gaussian form, and often specified in a relatively arbitrary manner. We combine our source reconstruction network with a convolutional neural network that predicts the parameters of the mass distribution in the lensing galaxies directly from telescope images, allowing a fully automated reconstruction of the background source images and the foreground mass distribution.