
There is a more recent version of this eprint available. Click here to view it.
Collaboration, LUX, Akerib, DS, Alsum, S et al. (97 more authors) (Submitted: 2022) Fast and flexible analysis of direct dark matter search data with machine learning. [Preprint - arXiv]
Abstract
We present the results from combining machine learning with the profile likelihood fit procedure, using data from the Large Underground Xenon (LUX) dark matter experiment. This approach demonstrates reduction in computation time by a factor of 30 when compared with the previous approach, without loss of performance on real data. We establish its flexibility to capture non-linear correlations between variables (such as smearing in light and charge signals due to position variation) by achieving equal performance using pulse areas with and without position-corrections applied. Its efficiency and scalability furthermore enables searching for dark matter using additional variables without significant computational burden. We demonstrate this by including a light signal pulse shape variable alongside more traditional inputs such as light and charge signal strengths. This technique can be exploited by future dark matter experiments to make use of additional information, reduce computational resources needed for signal searches and simulations, and make inclusion of physical nuisance parameters in fits tractable.
Metadata
Item Type: | Preprint |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 The Author(s). For reuse permissions, please contact the Author(s). |
Keywords: | astro-ph.CO; astro-ph.CO; astro-ph.IM; hep-ex; physics.ins-det |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Science (Sheffield) > Department of Physics and Astronomy (Sheffield) |
Funding Information: | Funder Grant number SCIENCE AND TECHNOLOGY FACILITIES COUNCIL ST/M003469/1 SCIENCE AND TECHNOLOGY FACILITIES COUNCIL ST/N001141/1 SCIENCE AND TECHNOLOGY FACILITIES COUNCIL ST/N000277/1 Science and Technology Facilities Council ST/N000277/1 SCIENCE AND TECHNOLOGY FACILITIES COUNCIL ST/P00573X/1 SCIENCE AND TECHNOLOGY FACILITIES COUNCIL ST/S000747/1 Science and Technology Facilities Council 2480818 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 01 Nov 2022 13:47 |
Last Modified: | 01 Nov 2022 13:47 |
Identification Number: | 10.48550/arXiv.2201.05734 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:192484 |
Available Versions of this Item
- Fast and flexible analysis of direct dark matter search data with machine learning. (deposited 01 Nov 2022 13:47) [Currently Displayed]