Domain-informed neural networks for interaction localization within astroparticle experiments

We propose a domain-informed neural network architecture for experimental particle physics, using particle interaction localization with the time-projection chamber (TPC) technology as an example application. While multilayer perceptrons (MLPs) have emerged as a leading contender for reconstruction in TPCs, this approach does not reflect prior knowledge of the underlying scientific processes. We encode prior detector knowledge, in terms of both signal characteristics and detector geometry, into the feature encoding and the output layers of a neural network. The resulting Domain-informed Neural Network (DiNN) limits the receptive fields of the neurons in the initial feature encoding layers to account for the spatially localized nature of the signals produced within the TPC, which significantly reduces the number of parameters in the network in comparison to an MLP. In addition, the output layers of the network are modified using two geometric transformations to ensure the DiNN produces localizations within the interior of the detector. The end result is a neural network architecture that has 60% fewer parameters than an MLP, but still achieves similar localization performance and provides a path to future architectural developments with improved performance.