Model-independent searches of new physics in DARWIN with a semi-supervised deep learning pipeline

TL;DR

This paper introduces a deep learning pipeline for model-independent, likelihood-free detection of anomalous events in the DARWIN liquid Xenon experiment, outperforming traditional methods and enabling more efficient analysis.

Contribution

A novel semi-supervised deep learning approach using variational autoencoders and classifiers for model-independent anomaly detection in dark matter searches.

Findings

Outperforms classical likelihood-based background rejection tests.

Learns relevant energy features directly from high-dimensional detector data.

Reduces computational effort and information loss by avoiding data compression.

Abstract

We present a novel deep learning pipeline to perform a model-independent, likelihood-free search for anomalous (i.e., non-background) events in the proposed next generation multi-ton scale liquid Xenon-based direct detection experiment, DARWIN. We train an anomaly detector comprising a variational autoencoder and a classifier on extensive, high-dimensional simulated detector response data and construct a one-dimensional anomaly score optimised to reject the background only hypothesis in the presence of an excess of non-background-like events. We benchmark the procedure with a sensitivity study that determines its power to reject the background-only hypothesis in the presence of an injected WIMP dark matter signal, outperforming the classical, likelihood-based background rejection test. We show that our neural networks learn relevant energy features of the events from low-level, high-dimensional detector outputs, without the need to compress this data into lower-dimensional observables, thus reducing computational effort and information loss. For the future, our approach lays the foundation for an efficient end-to-end pipeline that eliminates the need for many of the corrections and cuts that are traditionally part of the analysis chain, with the potential of achieving higher accuracy and significant reduction of analysis time.