A flexible event reconstruction based on machine learning and likelihood principles

Abstract

Event reconstruction is a central step in many particle physics experiments, turning detector observables into parameter estimates; for example estimating the energy of an interaction given the sensor readout of a detector. A corresponding likelihood function is often intractable, and approximations need to be constructed. In our work, we first show how the full likelihood for a many-sensor detector can be broken apart into smaller terms, and secondly how we can train neural networks to approximate all terms solely based on forward simulation. Our technique results in a fast, flexible, and close-to-optimal surrogate model proportional to the likelihood and can be used in conjunction with standard inference techniques allowing for a consistent treatment of uncertainties. We illustrate our technique for parameter inference in neutrino telescopes based on maximum likelihood and Bayesian posterior sampling. Given its great flexibility, we also showcase our method for geometry optimization enabling to learn optimal detector designs. Lastly, we apply our method to realistic simulation of a ton-scale water-based liquid scintillator detector.

References in corpus (3)

• Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube
• Implementation of a Gauss convoluted Pandel PDF for track reconstruction in Neutrino Telescopes
• Future Advances in Photon-Based Neutrino Detectors: A SNOWMASS White Paper

Cited by in corpus (6)

• EOS: a demonstrator of hybrid optical detector technology
• Accelerated Bayesian Inference for Molecular Simulations using Local Gaussian Process Surrogate Models
• Characterization of a radiation detector based on opaque water-based liquid scintillator
• Using Machine Learning to Separate Cherenkov and Scintillation Light in Hybrid Neutrino Detector
• Neural network ensemble for computing cross sections for rotational transitions in H${}_2$O + H${}_2$O collisions
• Refine Neutrino Events Reconstruction with BEiT-3