论文标题
部分可观测时空混沌系统的无模型预测
Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM
论文作者
论文摘要
从星系图像中去除光学和大气模糊可显着改善星系形状测量值，用于弱重力透镜和星系进化研究。这种不良的线性反问题通常通过正规化先验或深度学习增强的反卷积算法来解决。我们在星系调查中引入了一种所谓的“物理信息深度学习”方法（PSF）反卷积问题。我们将算法展开和插件技术应用于乘数的交替方向方法（ADMM），其中神经网络从模拟的星系图像中学习了适当的超参数和降解先导。我们表征了不同亮度水平的星系的几种方法的时间绩效折衷，以及我们方法对系统的PSF错误和网络消融的鲁棒性。与经典方法相比，我们显示出38.6％（SNR = 20）/45.0%（SNR = 200）的剪切椭圆度误差的改善和7.4％（SNR = 20）/33.2%（SNR = 200）与现代方法相比。
Removing optical and atmospheric blur from galaxy images significantly improves galaxy shape measurements for weak gravitational lensing and galaxy evolution studies. This ill-posed linear inverse problem is usually solved with deconvolution algorithms enhanced by regularisation priors or deep learning. We introduce a so-called "physics-informed deep learning" approach to the Point Spread Function (PSF) deconvolution problem in galaxy surveys. We apply algorithm unrolling and the Plug-and-Play technique to the Alternating Direction Method of Multipliers (ADMM), in which a neural network learns appropriate hyperparameters and denoising priors from simulated galaxy images. We characterise the time-performance trade-off of several methods for galaxies of differing brightness levels as well as our method's robustness to systematic PSF errors and network ablations. We show an improvement in reduced shear ellipticity error of 38.6% (SNR=20)/45.0% (SNR=200) compared to classic methods and 7.4% (SNR=20)/33.2% (SNR=200) compared to modern methods.
