Particle Hit Clustering and Identification Using Point Set Transformers in Liquid Argon Time Projection Chambers
This addresses the computational inefficiency of traditional methods for neutrino and dark-matter detection, offering significant speed and accuracy gains, though it is incremental as it builds on existing sparse matrix techniques.
The paper tackles the problem of particle hit clustering and identification in liquid argon time projection chambers by proposing a point set neural network that operates directly on sparse matrices, improving classification by up to 86% and segmentation by up to 71% while reducing runtime by up to 91% and memory usage by up to 66%.
Liquid argon time projection chambers are often used in neutrino physics and dark-matter searches because of their high spatial resolution. The images generated by these detectors are extremely sparse, as the energy values detected by most of the detector are equal to 0, meaning that despite their high resolution, most of the detector is unused in a particular interaction. Instead of representing all of the empty detections, the interaction is usually stored as a sparse matrix, a list of detection locations paired with their energy values. Traditional machine learning methods that have been applied to particle reconstruction such as convolutional neural networks (CNNs), however, cannot operate over data stored in this way and therefore must have the matrix fully instantiated as a dense matrix. Operating on dense matrices requires a lot of memory and computation time, in contrast to directly operating on the sparse matrix. We propose a machine learning model using a point set neural network that operates over a sparse matrix, greatly improving both processing speed and accuracy over methods that instantiate the dense matrix, as well as over other methods that operate over sparse matrices. Compared to competing state-of-the-art methods, our method improves classification performance by 14%, segmentation performance by more than 22%, while taking 80% less time and using 66% less memory. Compared to state-of-the-art CNN methods, our method improves classification performance by more than 86%, segmentation performance by more than 71%, while reducing runtime by 91% and reducing memory usage by 61%.