Speaker
Description
High-rate nuclear physics experiments require fast and accurate detector calibration to support continuous data collection and reconstruction. Time Projection Chambers (TPCs) are particularly sensitive to time-dependent space-charge distortions, which require frequent calibration updates and impose significant computational challenges.We present a machine-learning-based framework developed for the sPHENIX experiment at RHIC to accelerate TPC distortion corrections. A three-dimensional U-Net convolutional neural network trained on high-fidelity distortion maps achieves approximately two orders of magnitude speedup while preserving correction accuracy.
We discuss how this approach can enable near-real-time calibration in streaming data environments, reducing computational overhead while maintaining tracking precision. These developments provide a foundation for adaptive, AI-driven detector calibration at future high-rate experiments, including the Electron-Ion Collider.