CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters
2026-06-02 • Machine Learning
Machine Learning
AI summaryⓘ
The authors work on speeding up how particle showers are simulated in particle detectors, which usually takes a lot of computing time. They created a new method that combines smart math tools to generate these showers quickly, needing only one or a few steps to make accurate results. Their system learns directly from real data and uses physics rules during training to keep the simulated showers realistic. Tests show their approach matches or beats current leading methods while being much faster. This makes their work a promising way to do fast and reliable detector simulations in future experiments.
calorimeter simulationMonte Carlo methodsGeant4flow matchingdiffusion modelsgenerative modelsvelocity field integratorphysics-guided lossparticle showersfast simulation
Authors
Cheng Jiang, Sitian Qian, Kevin Pedro, Oz Amram, Huilin Qu, Maggie Voetberg
Abstract
High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of machine-learning surrogates for traditional Monte Carlo tools such as Geant4. Flow matching and diffusion-based generative models have become leading approaches for high-dimensional fast simulation because of their sample quality, but typically require ${\cal O}(100)$ function evaluations at inference and often rely on auxiliary networks to constrain global observables, compromising streamlined end-to-end generation. We introduce a unified framework that improves the balance between speed, shower quality, and physics fidelity. The method combines: (i) an average velocity field integrator that enables sampling in one or a few evaluations; (ii) a learned generative prior in shower space, constructed from data rather than random noise; and (iii) physics-guided loss terms that impose inductive biases on key observables during training. These elements are training time regularizers, preserving end-to-end inference with no additional cost. With only one or a few evaluation steps, the model achieves shower quality competitive with state-of-the-art flow and diffusion approaches, tested on several public high granularity calorimeter datasets. The results demonstrate inter-layer shower structure consistent with the underlying physics, providing a strong candidate for future fast simulation workflows.