MetaHEP: Meta learning for fast shower simulation of high energy physics experiments

Abstract

For High Energy Physics (HEP) experiments, such as the Large Hadron Collider (LHC) experiments, the calorimeter is a key detector to measure the energy of particles. Incident particles interact with the material of the calorimeter, creating cascades of secondary particles, so-called showers. A detailed description of the showering process relies on simulation methods that precisely describe all particle interactions with matter. Constrained by the need for precision, the simulation of calorimeters is inherently slow and constitutes a bottleneck for HEP analysis. Furthermore, with the upcoming high luminosity upgrade of the LHC and a much-increased data production rate, the amount of required simulated events will increase. Several research directions have recently investigated the use of Machine Learning based models to accelerate particular calorimeter response simulation. These models typically require a large amount of data and time for training, and the result is a simulation tuned specifically to this configuration. Meta-learning has emerged recently as a fast learning algorithm using small training datasets. In this paper, we use a meta-learning approach that “learns to learn” to generate showers from multiple calorimeter geometries, using a first-order gradient-based algorithm. We present MetaHEP, the first application of the meta-learning approach to accelerate shower simulation using very high granular data and using one of the calorimeters proposed for the Future Circular Collider (FCC), a next-generation of high-performance particle colliders.