Real-time calibrations for future detectors at FAIR

TL;DR

This paper presents a neural network-based real-time calibration method for FAIR detectors, combining LSTM and Graph Convolutions to achieve fast, stable, and accurate calibrations comparable to offline methods.

Contribution

The authors develop a novel LSTM-Graph Convolution hybrid neural network for real-time calibration, significantly reducing calibration time for high-rate data environments.

Findings

Achieved calibration accuracy comparable to offline methods

Reduced calibration time for real-time applications

Demonstrated stability and reliability in environmental data predictions

Abstract

The real-time data processing of the next generation of experiments conducted at FAIR requires a reliable reconstruction of event topologies and, therefore, will depend heavily on in-situ calibration procedures. A neural network-based approach can provide fast real-time calibrations based on continuously available environmental data. We applied this approach to the data obtained from the Drift Chambers of HADES. To enhance regularization we incorporate information about previous environmental states into the Long Short-Term Memory (LSTM) architecture and combine it with Graph Convolutions to account for correlations between different chambers. With the usage of a proposed prediction strategy we achieved stable and accurate predictions, matching the quality of an offline calibration. Moreover, our approach significantly reduces the calibration time, making it well-suited for real-time applications within high-rate data acquisition environments.