End-to-End Detector Optimization with Diffusion Models: A Case Study in Sampling Calorimeters

Recent advances in machine learning have opened new avenues for optimizing detector designs in high-energy physics, where the complex interplay of geometry, materials, and physics processes has traditionally posed a significant challenge. In this work, we introduce the end-to-end. AI Detector Optimization framework (AIDO), which leverages a diffusion model as a surrogate for the full simulation and reconstruction chain, enabling gradient-based design exploration in both continuous and discrete parameter spaces. Although this framework is applicable to a broad range of detectors, we illustrate its power using the specific example of a sampling calorimeter, focusing on charged pions and photons as representative incident particles. Our results demonstrate that the diffusion model effectively captures critical performance metrics for calorimeter design, guiding the automatic search for a layer arrangement and material composition that align with known calorimeter principles. The success of this proof-of-concept study provides a foundation for the future applications of end-to-end optimization to more complex detector systems, offering a promising path toward systematically exploring the vast design space in next-generation experiments.

Authors

Institutions

Publication Details

Journal
Particles
Published
2025-04-23
DOI
https://doi.org/10.3390/particles8020047
Citations
2
Primary Topic
Radiation Detection and Scintillator Technologies
Type
article
Field-Weighted Citation Impact
3.77

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

End-to-End Detector Optimization with Diffusion Models: A Case Study in Sampling Calorimeters

A. Breccia, A. De Vita, Muhammad Awais, Nicolas R. Gauger et al.
2 citations
Particles
Radiation Detection and Scintillator Technologies
3.77
article

End-to-End Detector Optimization with Diffusion Models: A Case Study in Sampling Calorimeters

A. Breccia, A. De Vita, Muhammad Awais, Nicolas R. Gauger, T. Dorigo, J. Kieseler, Abhishek, Fredrik Sandin, Kylian Schmidt, P. Vischia, Max Aehle, Long Chen, X. Nguyen, Federico Nardi, M. Klute, Enrico Lupi, Joseph Willmore, Riccardo Carroccio, Krishna Nikhil Kota
article en
2 citations

Abstract

Recent advances in machine learning have opened new avenues for optimizing detector designs in high-energy physics, where the complex interplay of geometry, materials, and physics processes has traditionally posed a significant challenge. In this work, we introduce the end-to-end. AI Detector Optimization framework (AIDO), which leverages a diffusion model as a surrogate for the full simulation and reconstruction chain, enabling gradient-based design exploration in both continuous and discrete parameter spaces. Although this framework is applicable to a broad range of detectors, we illustrate its power using the specific example of a sampling calorimeter, focusing on charged pions and photons as representative incident particles. Our results demonstrate that the diffusion model effectively captures critical performance metrics for calorimeter design, guiding the automatic search for a layer arrangement and material composition that align with known calorimeter principles. The success of this proof-of-concept study provides a foundation for the future applications of end-to-end optimization to more complex detector systems, offering a promising path toward systematically exploring the vast design space in next-generation experiments.

ParticlesVol. 8(2)
Karlsruhe Institute of Technology (DE), University of Padua (IT), University of Kaiserslautern (DE), National Institute of Science Education and Research (IN), Universidad de Oviedo (ES), Luleå University of Technology (SE), Istituto Nazionale di Fisica Nucleare, Sezione di Padova (IT), Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau (DE), Daimler (Germany) (DE)
European Commission, Knut och Alice Wallenbergs Stiftelse, Agencia Estatal de Investigación
Openalex Percentile: Top 8%
Radiation Detection and Scintillator Technologies
3.77
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.