Author:
Diefenbacher Sascha,Eren Engin,Gaede Frank,Kasieczka Gregor,Krause Claudius,Shekhzadeh Imahn,Shih David
Abstract
AbstractWe explore the use of normalizing flows to emulate Monte Carlo detector simulations of photon showers in a high-granularity electromagnetic calorimeter prototype for the International Large Detector (ILD). Our proposed method — which we refer to as “Layer-to-Layer Flows” (L2LFlows) — is an evolution of the CaloFlow architecture adapted to a higher-dimensional setting (30 layers of 10× 10 voxels each). The main innovation ofL2LFlowsconsists of introducing 30 separate normalizing flows, one for each layer of the calorimeter, where each flow is conditioned on the previous five layers in order to learn the layer-to-layer correlations. We compare our results to the BIB-AE, a state-of-the-art generative network trained on the same dataset and find our model has a significantly improved fidelity.
Subject
Mathematical Physics,Instrumentation
Reference58 articles.
1. GEANT4–a simulation toolkit;Agostinelli;Nucl. Instrum. Meth. A,2003
2. Geant4 developments and applications;Allison;IEEE Trans. Nucl. Sci.,2006
3. Recent developments in Geant4;Allison;Nucl. Instrum. Meth. A,2016
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献