https://doi.org/10.1140/epjc/s10052-025-15161-2
Regular Article - Experimental Physics
Model-independent searches of new physics in DARWIN with deep learning
1
Nikhef and the University of Groningen, Van Swinderen Institute, 9747AG, Groningen, The Netherlands
2
Kamioka Observatory, Institute for Cosmic Ray Research, and Kavli Institute for the Physics and Mathematics of the Universe (WPI), University of Tokyo,Hida, 506-1205, Higashi-Mozumi, Kamioka, Gifu, Japan
3
Physik-Institut, University of Zürich, 8057, Zürich, Switzerland
4
LPNHE, Sorbonne Université,CNRS/IN2P3, 75005, Paris, France
5
Institute for Nuclear Physics, University of Münster, 48149, Münster, Germany
6
Department of Physics and Astronomy, Rice University, 77005, Houston, TX, USA
7
INAF-Astrophysical Observatory of Torino, Department of Physics, University of Torino and INFN-Torino, 10125, Tourin, Italy
8
INFN-Laboratori Nazionali del Gran Sasso and Gran Sasso Science Institute, 67100, L’Aquila, Italy
9
Department of Physics, Enrico Fermi Institute & Kavli Institute for Cosmological Physics, University of Chicago, 60637, Chicago, IL, USA
10
Vinca Institute of Nuclear Science, University of Belgrade, Mihajla Petrovica Alasa 12-14, Belgrade, Serbia
11
Physics Department, Columbia University, 10027, New York, NY, USA
12
Department of Physics & Astronomy, University of Alabama, 34587-0324, Tuscaloosa, AL, USA
13
Institute for Data Processing and Electronics, Karlsruhe Institute of Technology, 76021, Karlsruhe, Germany
14
ARC Centre of Excellence for Dark Matter Particle Physics, School of Physics, The University of Melbourne, 3010, Vic, Australia
15
SUBATECH, IMT Atlantique, CNRS/IN2P3, Nantes Université, 44307, Nantes, France
16
Department of Physics and Astronomy, University of Bologna and INFN-Bologna, 40126, Bologna, Italy
17
Max-Planck-Institut für Kernphysik, 69117, Heidelberg, Germany
18
Institute for Astroparticle Physics, Karlsruhe Institute of Technology, 76021, Karlsruhe, Germany
19
School of Physics, The University of Sydney, 2006, Camperdown, Sydney, NSW, Australia
20
Department of Particle Physics and Astrophysics, Weizmann Institute of Science, 7610001, Rehovot, Israel
21
Institute of Experimental Particle Physics, Karlsruhe Institute of Technology, 76021, Karlsruhe, Germany
22
Physikalisches Institut, Universität Freiburg, 79104, Freiburg, Germany
23
Physikalisches Institut, Universität Freiburg, 79104, Freiburg, (Now at Sheffield), Germany
24
Department of Physics and Astronomy, University of Sheffield, S3 7RH, Sheffield, UK
25
Department of Physics & Center for High Energy Physics, Tsinghua University, 100084, Beijing, People’s Republic of China
26
Physikalisches Institut, Universität Heidelberg, Heidelberg, Germany
27
Nikhef and the University of Amsterdam, Science Park, 1098XG, Amsterdam, The Netherlands
28
Oskar Klein Centre, Department of Physics, Stockholm University, 10691, AlbaNova, Stockholm, Sweden
29
Institut für Physik & Exzellenzcluster PRISMA+, Johannes Gutenberg-Universität Mainz, 55099, Mainz, Germany
30
Department of Physics and Chemistry, University of L’Aquila, 67100, L’Aquila, Italy
31
Kobayashi-Maskawa Institute for the Origin of Particles and the Universe, and Institute for Space-Earth Environmental Research, Nagoya University, 464-8602, Furo-cho, Chikusa-ku, Nagoya, Aichi, Japan
32
Department of Physics “Ettore Pancini”, University of Napoli and INFN-Napoli, 80126, Napoli, Italy
33
Department of Physics and Astronomy, Purdue University, 47907, West Lafayette, IN, USA
34
Albert Einstein Center for Fundamental Physics, Institute for Theoretical Physics, University of Bern, Sidlerstrasse 5, 3012, Bern, Switzerland
35
Department of Physics, University of California San Diego, 92093, La Jolla, CA, USA
36
Department of Physics and Astronomy, University College London (UCL), WC1E 6BT, London, UK
37
Department of Physics & Astronomy, Bucknell University, Lewisburg, PA, USA
38
Kirchhoff-Institut für Physik, Universität Heidelberg, Heidelberg, Germany
39
Department of Physics, School of Science, Westlake University, 310030, Hangzhou, People’s Republic of China
40
School of Science and Engineering, The Chinese University of Hong Kong, 518172, Shenzhen, Guangdong, People’s Republic of China
41
LIBPhys, Department of Physics, University of Coimbra, 3004-516, Coimbra, Portugal
42
Physics Department, Imperial College London Blackett Laboratory, SW7 2AZ, London, UK
43
Department of Quantum Physics and Astrophysics and Institute of Cosmos Sciences, University of Barcelona, 08028, Barcelona, Spain
44
Department of Physics, Kobe University, 657-8501, Kobe, Hyogo, Japan
45
Theoretical and Scientific Data Science, Scuola Internazionale Superiore di Studi Avanzati (SISSA), 34136, Trieste, Italy
46
Department of Physics, Technische Universitaät Darmstadt, 64289, Darmstadt, Germany
47
INFN-Ferrara and Dip. di Fisica e Scienze della Terra, Università di Ferrara, 44122, Ferrara, Italy
48
Technische Universität Dresden, 01069, Dresden, Germany
49
University of Banja Luka, 78000, Banja Luka, Bosnia and Herzegovina
50
INFN-Roma Tre, 00146, Roma, Italy
51
Coimbra Polytechnic - ISEC, 3030-199, Coimbra, Portugal
52
University of Grenada, Grenada, Spain
53
Department of Physics and Astronomy, University of Sheffield, S3 7RH, Sheffield, UK
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
21
October
2024
Accepted:
3
December
2025
Published online:
26
March
2026
Abstract
We present a 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 (VAE) and a classifier on high-dimensional simulated detector response data and construct a 1D anomaly score to reject the background-only hypothesis in the presence of an excess of non-background-like events. We use simulated validation data to determine the power of the method to reject the background-only hypothesis in the presence of a WIMP dark matter signal, without any model-dependent assumption about the nature of the signal. We show that our neural networks learn relevant features of the events from low-level, high-dimensional detector outputs, avoiding lossy and computationally expensive compression into lower-dimensional observables. Our approach is complementary to the usual likelihood-based analysis, in that it reduces the reliance on 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. We envisage the methodology presented in this work augmenting or complementing likelihood-based and other data-driven methods currently utilized in the DARWIN (and in the future, XLZD) analysis pipeline.
© The Author(s) 2026
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Funded by SCOAP3.
