2021/10/31 by Juan Herrero-García, Juan Herrero-Garcia, Riley Patrick +1 · 19 citations
Physics and Astronomy · #Anomaly (physics) #Anomaly detection #Artificial intelligence #Artificial neural network #Autoencoder #Computer science #Context (archaeology) #Convolutional neural network #Cosmology and Gravitation Theories #Dark Matter and Cosmic Phenomena #Deep learning #Feature learning #Inference #Machine learning #Particle physics theoretical and experimental studies #Pattern recognition (psychology) #Physics #Representation (politics) #Supervised learning #Unsupervised learning #hep-ph
paper · pdf · open access · doi:10.1088/1475-7516/2022/02/039
published in Journal of Cosmology and Astroparticle Physics 2022(02), 039 (Institute of Physics) · Matches published version in JCAP
openalex publication_date 2022/02/01 · arxiv created 2022/02/28 · arxiv updated 2022/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The dark matter sector remains completely unknown. It is therefore crucial to keep an open mind regarding its nature and possible interactions. Focusing on the case of Weakly Interacting Massive Particles, in this work we make this general philosophy more concrete by applying modern machine learning techniques to dark matter direct detection. We do this by encoding and decoding the graphical representation of background events in the XENONnT experiment with a convolutional variational autoencoder. We describe a methodology that utilizes the `anomaly score' derived from the reconstruction loss of the convolutional variational autoencoder as well as a pre-trained standard convolutional neural network, in a semi-supervised fashion. Indeed, we observe that optimum results are obtained only when both unsupervised and supervised anomaly scores are considered together. A data set that has a higher proportion of anomaly score is deemed anomalous and deserves further investigation. Contrary to classical analyses, in principle all information about the events is used, preventing unnecessary information loss. Lastly, we demonstrate the reach of learning-focused anomaly detection in this context by comparing results with classical inference, observing that, if tuned properly, these techniques have the potential to outperform likelihood-based methods.