Towards a method to anticipate dark matter signals with deep learning at the LHC
This work addresses the challenge of identifying dark matter signals in particle physics experiments, offering a flexible method for model testing, but it is incremental as it builds on existing deep learning approaches with a data organization tweak.
The researchers tackled the problem of detecting dark matter signals at the LHC by using neural networks on 2D histogram data instead of event-by-event arrays, resulting in a large performance boost for distinguishing between standard model and new physics signals, with performance independent of background event counts when scaled by S/√B.
We study several simplified dark matter (DM) models and their signatures at the LHC using neural networks. We focus on the usual monojet plus missing transverse energy channel, but to train the algorithms we organize the data in 2D histograms instead of event-by-event arrays. This results in a large performance boost to distinguish between standard model (SM) only and SM plus new physics signals. We use the kinematic monojet features as input data which allow us to describe families of models with a single data sample. We found that the neural network performance does not depend on the simulated number of background events if they are presented as a function of $S/\sqrt{B}$, where $S$ and $B$ are the number of signal and background events per histogram, respectively. This provides flexibility to the method, since testing a particular model in that case only requires knowing the new physics monojet cross section. Furthermore, we also discuss the network performance under incorrect assumptions about the true DM nature. Finally, we propose multimodel classifiers to search and identify new signals in a more general way, for the next LHC run.