Application of sequence learning for predicting radiation damage of the CMS electromagnetic calorimeter

Mario Ivan Gallegos Torres; Leonid Serkin; Guy Paic

physics.ins-detOct 2, 2026

Application of sequence learning for predicting radiation damage of the CMS electromagnetic calorimeter

Authors: Mario Ivan Gallegos Torres, Leonid Serkin, Guy Paic

Organizations: Facultad de Ciencias, Universidad Nacional Autónoma de México, Circuito Exterior s/n, Ciudad de México 04510, México. · Instituto de Ciencias Nucleares, Universidad Nacional Autónoma de México, Apartado Postal 70-543, Ciudad de México 04510, México.

Abstract

In this paper we use machine learning methods to predict radiation damage in the lead tungstate crystals of the CMS electromagnetic calorimeter at the Large Hadron Collider. We analyze LHC Open Data collected from 2016 to 2018 and study the time evolution of the crystal optical transparency. We apply deep neural network models to predict its behavior over different future time intervals, and find that encoder-decoder sequence-to-sequence architectures can effectively describe crystal aging.

Figures & tables

Panel of Figure 1 — Figure 1: (a) Schematic of the ECAL system of the CMS experiment at the LHC. (b) PbWO 4 crystals used in the CMS ECAL.

Figure 2: Seq2Seq architecture used in this work.

Panel of Figure 3 — Figure 3: Comparison between the true (blue line) and predicted (red line) calibration for ECAL crystal (a) 30600 and (b) 54000 as a function of time, using a 12-step prediction horizon. The lower panel displays the integrated daily luminosity.

Panel of Figure 4 — Figure 4: (a) Results reported by Joshi et al. [ 7 ] , including the original 2017 Case 1 (green). (b) Comparison of this result (green) with the corrected code implementation (blue), and comparison with the Seq2Seq model (yellow) developed in this paper. All results are shown for ECAL crystal 54000.

Explore similar work

Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
Apr 7, 2026Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi +4Adversarial Robustness Adversarial Attacks
CERN, Geneva, Switzerland · RWTH Aachen University, Aachen, Germany · DESY, Hamburg, Germany
Enabling Low-Latency Machine learning on Radiation-Hard FPGAs with hls4ml
Feb 17, 2026Katya Govorkova, Julian Garcia Pardinas, Vladimir Loncar +5FPGA-Based Neural Network Acceleration Efficient Neural Network Inference
Massachusetts Institute of Technology (MIT), 77 Massachusetts Ave, Cambridge, MA 02139, USA · Department of Experimental Physics, European Organization for Nuclear Research (CERN), 1211 Geneva 23, Switzerland · University of Milano-Bicocca (Italy), and Department of Experimental Physics, European Organization for Nuclear Research (CERN), 1211 Geneva 23, Switzerland
Suppression of $^{14}\mathrm{C}$ photon hits in large liquid scintillator detectors via spatiotemporal deep learning
Mar 29, 2026Junle Li, Zhaoxiang Wu, Guanda Gong +5High-Energy Physics
School of Aeronautics and Astronautics, Zhejiang University, Hangzhou 310027, China · Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, China · School of Physical Sciences, University of Chinese Academy of Science, Beijing 100049, China +1

Apr 7, 2026J/K move · Enter open · S save

Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment

Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi, Eloise Matheson+3

CERN, Geneva, Switzerland · RWTH Aachen University, Aachen, Germany · DESY, Hamburg, Germany

Adversarial Robustness Adversarial Attacks Time Series Classification Adversarial Training High-Energy Physics

Open paper AskPDF arXiv

In this paper, we analyze and improve the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at CERN's Large Hadron Collider (LHC) by classifying a beam-loss monitor (BLM) time series during crystal rotation. We formalize a local robustness property for this classifier under an adversarial threat model based on real-world plausibility. Building on established parameterized input-transformation patterns used for transformation- and semantic-perturbation robustness, we instantiate a preprocessing-aware wrapper for our deployed time-series pipeline: we encode time-series normalization, padding constraints, and structured perturbations as a lightweight differentiable wrapper in front of the CNN, so that existing gradient-based robustness frameworks can operate on the deployed pipeline. For formal verification, data-dependent preprocessing such as per-window z-normalization introduces nonlinear operators that require verifier-specific abstractions. We therefore focus on attack-based robustness estimates and pipeline-checked validity by benchmarking robustness with the frameworks Foolbox and ART. Adversarial fine-tuning of the resulting CNN improves robust accuracy by up to 18.6 % without degrading clean accuracy. Finally, we extend robustness on time-series data beyond single windows to sequence-level robustness for sliding-window classification, introduce adversarial sequences as counterexamples to a temporal robustness requirement over full scans, and observe attack-induced misclassifications that persist across adjacent windows.

Abstract

Explore similar work

Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment

Enabling Low-Latency Machine learning on Radiation-Hard FPGAs with hls4ml

Suppression of 14C^{14}\mathrm{C}14C photon hits in large liquid scintillator detectors via spatiotemporal deep learning

Suppression of $^{14}\mathrm{C}$ photon hits in large liquid scintillator detectors via spatiotemporal deep learning