Description
Traditional Monte Carlo methods for simulating photon propagation in water Cherenkov detectors are computationally expensive and challenging to optimize using calibration data. In this work, we introduce a novel machine learning approach to simulate photon transport using fast surrogate models. We also demonstrate how these models can be efficiently fine-tuned with calibration data to improve accuracy and performance.
Speaker
Ka Ming Tsui
(Kavli Institute for the Physics and Mathematics of the Universe, University of Tokyo)