Improving smuon searches with neural networks
Abstract We demonstrate that neural networks can be used to improve search strategies, over existing strategies, in LHC searches for light electroweak-charged scalars that decay to a muon and a heavy invisible fermion. We propose a new search involving a neural network discriminator as a final cut a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | European Physical Journal C: Particles and Fields |
| Online Access: | https://doi.org/10.1140/epjc/s10052-025-13748-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585445043601408 |
|---|---|
| author | Alan S. Cornell Benjamin Fuks Mark D. Goodsell Anele M. Ncube |
| author_facet | Alan S. Cornell Benjamin Fuks Mark D. Goodsell Anele M. Ncube |
| author_sort | Alan S. Cornell |
| collection | DOAJ |
| description | Abstract We demonstrate that neural networks can be used to improve search strategies, over existing strategies, in LHC searches for light electroweak-charged scalars that decay to a muon and a heavy invisible fermion. We propose a new search involving a neural network discriminator as a final cut and show that different signal regions can be defined using networks trained on different subsets of signal samples (distinguishing low-mass and high-mass regions). We also present a workflow using publicly-available analysis tools, that can lead, from background and signal simulation, to network training, through to finding projections for limits using an analysis and ONNX libraries to interface network and recasting tools. We provide an estimate of the sensitivity of our search from Run 2 LHC data, and projections for higher luminosities, showing a clear advantage over previous methods. |
| format | Article |
| id | doaj-art-a6429fc4805a4f8ba313434d332fec3c |
| institution | Kabale University |
| issn | 1434-6052 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Physical Journal C: Particles and Fields |
| spelling | doaj-art-a6429fc4805a4f8ba313434d332fec3c2025-01-26T12:49:26ZengSpringerOpenEuropean Physical Journal C: Particles and Fields1434-60522025-01-0185111310.1140/epjc/s10052-025-13748-3Improving smuon searches with neural networksAlan S. Cornell0Benjamin Fuks1Mark D. Goodsell2Anele M. Ncube3Department of Physics, University of JohannesburgLaboratoire de Physique Théorique et Hautes Énergies (LPTHE), UMR 7589, Sorbonne Université and CNRSLaboratoire de Physique Théorique et Hautes Énergies (LPTHE), UMR 7589, Sorbonne Université and CNRSDepartment of Physics, University of JohannesburgAbstract We demonstrate that neural networks can be used to improve search strategies, over existing strategies, in LHC searches for light electroweak-charged scalars that decay to a muon and a heavy invisible fermion. We propose a new search involving a neural network discriminator as a final cut and show that different signal regions can be defined using networks trained on different subsets of signal samples (distinguishing low-mass and high-mass regions). We also present a workflow using publicly-available analysis tools, that can lead, from background and signal simulation, to network training, through to finding projections for limits using an analysis and ONNX libraries to interface network and recasting tools. We provide an estimate of the sensitivity of our search from Run 2 LHC data, and projections for higher luminosities, showing a clear advantage over previous methods.https://doi.org/10.1140/epjc/s10052-025-13748-3 |
| spellingShingle | Alan S. Cornell Benjamin Fuks Mark D. Goodsell Anele M. Ncube Improving smuon searches with neural networks European Physical Journal C: Particles and Fields |
| title | Improving smuon searches with neural networks |
| title_full | Improving smuon searches with neural networks |
| title_fullStr | Improving smuon searches with neural networks |
| title_full_unstemmed | Improving smuon searches with neural networks |
| title_short | Improving smuon searches with neural networks |
| title_sort | improving smuon searches with neural networks |
| url | https://doi.org/10.1140/epjc/s10052-025-13748-3 |
| work_keys_str_mv | AT alanscornell improvingsmuonsearcheswithneuralnetworks AT benjaminfuks improvingsmuonsearcheswithneuralnetworks AT markdgoodsell improvingsmuonsearcheswithneuralnetworks AT anelemncube improvingsmuonsearcheswithneuralnetworks |