Understanding the behaviour of subatomic particles traversing dense materials, often immersed in magnetic fields, has been crucial to their discovery, detection, identification, and reconstruction. It is a critical component for exploiting any particle detector. Modern radiation detectors have evolved towards 'imaging detectors', in which elementary particles leave individual traces called 'tracks'. 

These imaging detectors require a 'particle flow' reconstruction: particle signatures are precisely reconstructed in three dimensions, and the primary particle's kinematics (energy and momentum vector) can be measured track-by-track. This also means that a greater number of details can be obtained on each particle. These features open the question of which methods are best suited to handle the 'images' created by the subatomic particles.

Neural nets, inherited from natural language processing, are very close to the concept of a Bayesian filter that adopts a hyper-informative prior. Hence, they become excellent tools for drastically improving the accuracy and resolution of elementary particle trajectories.

Deep learning and particle physics

Deep learning is starting to play a more relevant role in designing and exploiting particle physics experiments. However, it is still in a gestation phase within the high-energy physics community. If the optimal neural network is optimised, deep learning has the unique capability of building a non-linear multi-dimensional MC-based prior probability function with many degrees of freedom (d.o.f.) that can efficiently and accurately model all the information acquired in a particle physics experiment and enhance the performance of the particle track fitting and, consequently, its kinematics reconstruction. Such a level of detail is, otherwise, nearly impossible to incorporate "by hand" in the form of, for example, a covariance matrix to be used in a traditional particle filter.

Milestone in AI applications

The researchers believe this approach is a milestone in artificial intelligence applications in HEP and can play the role of a game changer by shifting the paradigm in reconstructing particle interactions in the detectors. The prior, consciously built from modelling the underlying physics from data external to the experiment, becomes as essential as the data collected for the physics measurement. De facto, the prior provides a strong constraint to the 'interpretation' of the data, helping to remove outliers introduced by detector effects, such as from the smearing introduced by the point spread function and improving the spatial resolution well below the actual granularity of the detector.

Its accuracy also depends on the quality of the training sample, i.e., on the capability of the MC simulation to reproduce the data correctly. Although this is true for most of the charged particles, a careful characterisation of the detector response will be crucial to validate and, if necessary, tune the simulation (e.g., electromagnetic shower development or hadronic secondary interactions) used to generate the training sample.