Machine Learning Enables Real-Time Waveform Decomposition for Dual-Readout Calorimetry

TL;DR

This paper compares machine learning and template fitting methods for real-time separation of Cherenkov and scintillation signals in dual-readout calorimeters, demonstrating ML's efficiency at lower sampling rates and FPGA-compatible processing.

Contribution

It provides a systematic comparison of ML and template fitting for signal separation in dual-readout calorimeters, highlighting ML's advantages for real-time applications.

Findings

ML models achieve comparable performance at lower sampling rates.

A single ML model trained across energies shows robust performance.

FPGA-compatible compression enables real-time processing with low latency.

Abstract

Dual-readout calorimeters achieve superior energy resolution by simultaneously measuring Cherenkov and scintillation signals for event-by-event electromagnetic fraction correction, making them attractive for next-generation Higgs factories. However, if a full waveform readout is required for time-based analysis to separate Cherenkov and scintillation signals, high off-detector data rates might present challenges. These challenges can be mitigated by real-time signal processing in front-end electronics. We present a systematic comparison of machine learning (ML) and template fitting approaches for the separation of scintillation and Cherenkov light components in homogeneous dual-readout calorimeters across three representative crystal types. ML models achieve comparable signal extraction performance at lower sampling rates than template fitting. A single model trained over a range of incident particle energies demonstrates robust performance, and FPGA-compatible compression achieves latencies suitable for real-time application. This work establishes both baseline template fitting performance and ML-enhanced alternatives for crystal-based dual-readout calorimeters, offering practical pathways towards front-end feature extraction in future detector design.