Neural network clusterization for the ALICE TPC online computing

The ALICE Time Projection Chamber (TPC) is the detector with the highest data rate of the ALICE experiment at CERN and is the central detector for tracking and particle identification. Efficient online computing such as clusterization and tracking are mainly performed on GPUs with throughputs of approximately 900 GB/s. Clusterization, in particular, has a well-established foundation, with a variety of algorithms within the field of machine learning. This work investigates a neural network approach to cluster rejection and regression on a topological basis. Central to its task are the center-of-gravity, sigma and total charge estimation as well as rejection of clusters in the TPC readout. Additionally, a momentum vector estimate is made from the 3D input across readout rows in combination with reconstructed tracks which can benefit track seeding. Performance studies on inference speed as well as model architectures and physics performance on Monte Carlo data are presented, showing that tracking performance can be maintained while rejecting 5–10% of raw clusters with a ~30% reduced cluster fake rate compared to the current GPU clusterizer.