Title: AI for Science at BNL

Abstract: In this presentation, we will provide an overview of how AI/ML techniques are utilized in scientific research at BNL. We will delve into two specific use cases in greater detail. The first use case centers around computer vision applications for analyzing galaxy images. Within this context, we will focus on two key tasks: galaxy deblending, which involves separating individual galaxies from images that contain multiple galaxies overlapping with one another, and galaxy image deblurring, which entails reconstructing clear galaxy images from degraded astronomical images caused by factors such as the optical system, atmospheric conditions, and noise. Our second use case involves phase retrieval in Bragg coherent diffraction imaging.

Bio: Yuewei Lin (https://ywlincq.github.io/), is at Brookhaven National Laboratory as a computational scientist. His research interests include machine learning, computer vision and their applications in scientific data analysis.