{
  "abstract": "We present the $N$-fit algorithm designed to improve the reconstruction of neutrino events detected by a single line of the ANTARES underwater telescope, usually associated with low energy neutrino events ($\\sim$ 100 GeV). $N$-Fit is a neural network model that relies on deep learning and combines several advanced techniques in machine learning --deep convolutional layers, mixture density output layers, and transfer learning. This framework divides the reconstruction process into two dedicated branches for each neutrino event topology --tracks and showers-- composed of sub-models for spatial estimation --direction and position-- and energy inference, which later on are combined for event classification. Regarding the direction of single-line events, the $N$-Fit algorithm significantly refines the estimation of the zenithal angle, and delivers reliable azimuthal angle predictions that were previously unattainable with traditional $χ^2$-fit methods. Improving on energy estimation of single-line events is a tall order; $N$-Fit benefits from transfer learning to efficiently integrate key characteristics, such as the estimation of the closest distance from the event to the detector. $N$-Fit also takes advantage from transfer learning in event topology classification by freezing convolutional layers of the pretrained branches. Tests on Monte Carlo simulations and data demonstrate a significant reduction in mean and median absolute errors across all reconstructed parameters. The improvements achieved by $N$-Fit highlight its potential for advancing multimessenger astrophysics and enhancing our ability to probe fundamental physics beyond the Standard Model using single-line events from ANTARES data.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2511.16614",
  "author_total": 140,
  "authors": [
    {
      "name": "A Albert"
    },
    {
      "name": "S Alves"
    },
    {
      "name": "M André"
    },
    {
      "name": "M Ardid"
    },
    {
      "name": "S Ardid"
    },
    {
      "name": "J.-J Aubert"
    },
    {
      "name": "J Aublin"
    },
    {
      "name": "B Baret"
    },
    {
      "name": "S Basa"
    },
    {
      "name": "Y Becherini"
    },
    {
      "name": "B Belhorma"
    },
    {
      "name": "F Benfenati"
    },
    {
      "name": "V Bertin"
    },
    {
      "name": "S Biagi"
    },
    {
      "name": "J Boumaaza"
    },
    {
      "name": "M Bouta"
    },
    {
      "name": "M.C Bouwhuis"
    },
    {
      "name": "H Brânzaş"
    },
    {
      "name": "R Bruijn"
    },
    {
      "name": "J Brunner"
    },
    {
      "name": "J Busto"
    },
    {
      "name": "B Caiffi"
    },
    {
      "name": "D Calvo"
    },
    {
      "name": "S Campion"
    },
    {
      "name": "A Capone"
    },
    {
      "name": "F Carenini"
    },
    {
      "name": "J Carr"
    },
    {
      "name": "V Carretero"
    },
    {
      "name": "T Cartraud"
    },
    {
      "name": "S Celli"
    },
    {
      "name": "L Cerisy"
    },
    {
      "name": "M Chabab"
    },
    {
      "name": "R. Cherkaoui El Moursli"
    },
    {
      "name": "T Chiarusi"
    },
    {
      "name": "M Circella"
    },
    {
      "name": "J.A.B Coelho"
    },
    {
      "name": "A Coleiro"
    },
    {
      "name": "R Coniglione"
    },
    {
      "name": "P Coyle"
    },
    {
      "name": "A Creusot"
    },
    {
      "name": "A.F Díaz"
    },
    {
      "name": "B de Martino"
    },
    {
      "name": "C Distefano"
    },
    {
      "name": "I Di Palma"
    },
    {
      "name": "C Donzaud"
    },
    {
      "name": "D Dornic"
    },
    {
      "name": "D Drouhin"
    },
    {
      "name": "T Eberl"
    },
    {
      "name": "A Eddymaoui"
    },
    {
      "name": "T van Eeden"
    },
    {
      "name": "D van Eijk"
    },
    {
      "name": "S. El Hedri"
    },
    {
      "name": "N. El Khayati"
    },
    {
      "name": "A Enzenhöfer"
    },
    {
      "name": "P Fermani"
    },
    {
      "name": "G Ferrara"
    },
    {
      "name": "F Filippini"
    },
    {
      "name": "L Fusco"
    },
    {
      "name": "S Gagliardini"
    },
    {
      "name": "J García-Méndez"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/adcefwbfg52y4.bib",
  "cited_by": 0,
  "doi": "10.1088/2632-2153/ae5d84",
  "fulltext_url": null,
  "id": "adcefwbfg52y4",
  "issns": [
    "2632-2153",
    "2632-2153"
  ],
  "landing_url": "https://hal.science/hal-05397585v2",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.phys"
    ],
    [
      "hal",
      "1.phys.phys"
    ],
    [
      "hal",
      "2.phys.phys.phys-ins-det"
    ],
    [
      "openalex",
      "3106|Neutrino Physics Research"
    ]
  ],
  "openalex": "W7159584813",
  "pdf_url": "https://hal.science/hal-05397585/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": "IOP Publishing Ltd",
  "ris": "https://research.draconitic.com/paper/adcefwbfg52y4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:54Z",
      "native_id": "hal-05397585",
      "source": "hal",
      "url": "https://hal.science/hal-05397585v2"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "hal:2.phys.phys.phys-ins-det",
      "subfield": "applied-instrumentation"
    }
  ],
  "title": "Deep Learning Framework for Enhanced Neutrino Reconstruction of Single-line Events in the ANTARES Telescope",
  "title_text": "Deep Learning Framework for Enhanced Neutrino Reconstruction of Single-line Events in the ANTARES Telescope",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:54Z",
  "url": "https://research.draconitic.com/paper/adcefwbfg52y4",
  "venue": "Machine Learning : Science and Technology",
  "versions": []
}