Title: Physics-Informed Machine Learning for precise and accurate weak lensing shear estimation（用对称性教机器学习：弱引力透镜剪切的精确测量）
Speaker：Shurui Lin（University of Illinois, Urbana Champaign）

Abstract:

Weak gravitational lensing has served as an important probe for large-scale structure and cosmology for decades. Stage-IV surveys require both sub-percent calibration accuracy and high statistical precision for WL shear estimation, yet traditional estimators struggle with realistic galaxy complexity while machine-learning methods often introduce biases.

I will introduce a physics-informed machine-learning approach that combines a fully D₄-equivariant convolutional neural network (D₄CNN) with a score-matching technique for optimal shear estimation. The D₄CNN enforces symmetry under rotations and reflections, eliminating even-order shear biases by construction, while Analytical Calibration (AnaCal) provides precise, gradient-based self-calibration.

Together with modern denoising-score-matching framework, our method achieves multiplicative biases consistent with zero at the ∼10⁻⁴ level, well within the requirement of Stage IV surveys like LSST, and reduces shape noise by ∼20% relative to the classical baseline, (equivalent to ∼40% increase in observation time), providing a principled and practical machine-learning pathway toward optimal shear estimation for Stage-IV surveys.

Bio:
Shurui Lin is currently a 2nd-yr graduate student in University of Illinois, Urbana-Champaign, working with Prof.Xin Liu, after getting his bachelor’s degree of physics from University of Science and Technology of China. He now works in LSST-DESC on weak-lensing shear estimation. His research focus is applying machine learning technique for weak-lensing cosmology. 

Time: 14:00-16:00, 8/June, Monday
Venue: Room 506 (Large seminar room), Department of Astronomy