Calorimeter shower superresolution
This work addresses a domain-specific problem for particle physics researchers by providing an incremental improvement to fast calorimeter simulation models.
The paper tackles the computational bottleneck of simulating high-dimensional calorimeter showers at the Large Hadron Collider by introducing SuperCalo, a flow-based superresolution model that quickly upsamples coarse-grained showers into fine-grained ones, reducing computational cost, memory requirements, and generation time while maintaining high-fidelity variation.
Calorimeter shower simulation is a major bottleneck in the Large Hadron Collider computational pipeline. There have been recent efforts to employ deep-generative surrogate models to overcome this challenge. However, many of best performing models have training and generation times that do not scale well to high-dimensional calorimeter showers. In this work, we introduce SuperCalo, a flow-based superresolution model, and demonstrate that high-dimensional fine-grained calorimeter showers can be quickly upsampled from coarse-grained showers. This novel approach presents a way to reduce computational cost, memory requirements and generation time associated with fast calorimeter simulation models. Additionally, we show that the showers upsampled by SuperCalo possess a high degree of variation. This allows a large number of high-dimensional calorimeter showers to be upsampled from much fewer coarse showers with high-fidelity, which results in additional reduction in generation time.