{
  "abstract": "Strong gravitational lensing provides a powerful probe of dark matter, particularly on small scales where the gravitational effects of dark matter subhaloes within galaxies can manifest as perturbations within the extended arcs of gravitationally lensed sources. We investigate whether transforming lensed images into polar coordinates improves the ability of convolutional neural networks to infer subhalo mass. We introduce a machine learning architecture that outputs a prediction uncertainty alongside a mass prediction to enable assessment of network reliability. Using simulated Hubble Space Telescope observations, we compare our models trained on Cartesian and polar representations under different initialization schemes, noise levels, and subhalo concentrations ($c=60$, $c=30$). We find that polar-transformed inputs consistently yield higher subhalo detection fractions than standard Cartesian images across all tested masses. For subhaloes with mass $10^9\\mathrm{ M}_\\odot \\le M \\le 10^{9.5}\\mathrm{ M}_\\odot$, the fraction of subhaloes the network is able to detect increases by $\\sim 15$ per cent. Pretrained networks outperform randomly initialized networks, and the polar transform consistently improves network performance in both low signal-to-noise data and for lower-concentration subhaloes. These results demonstrate that presenting strong lensing images in a polar representation provides a computationally inexpensive way of improving convolutional neural network (CNN)-based subhalo detection.",
  "abstract_shown": true,
  "affiliations": [
    "School of Physics and Astronomy, University of Nottingham , University Park, Nottingham NG7 2RD ,"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "J M Campbell",
      "orcid": "0009-0001-4574-1027"
    },
    {
      "affs": [
        0
      ],
      "name": "S Dye",
      "orcid": "0000-0002-1318-8343"
    },
    {
      "affs": [
        0
      ],
      "name": "E Chapman",
      "orcid": "0000-0002-5050-9847"
    },
    {
      "affs": [
        0
      ],
      "name": "A Moss"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/197maatzmad7n.bib",
  "cited_by": 0,
  "doi": "10.1093/mnras/stag1955",
  "fulltext_url": null,
  "id": "197maatzmad7n",
  "issns": [
    "0035-8711",
    "1365-2966"
  ],
  "landing_url": "https://academic.oup.com/mnras/article/doi/10.1093/mnras/stag1955/8923674",
  "language": null,
  "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": [
    [
      "openalex",
      "3103|Galaxies: Formation, Evolution, Phenomena"
    ]
  ],
  "openalex": "W7167604255",
  "pdf_url": "https://academic.oup.com/mnras/advance-article-pdf/doi/10.1093/mnras/stag1955/71990220/stag1955.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": "Oxford University Press (OUP)",
  "ris": "https://research.draconitic.com/paper/197maatzmad7n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:17Z",
      "native_id": "10.1093/mnras/stag1955",
      "source": "crossref",
      "url": "https://academic.oup.com/mnras/article/doi/10.1093/mnras/stag1955/8923674"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "openalex:3103|Galaxies: Formation, Evolution, Phenomena",
      "subfield": "galaxies"
    }
  ],
  "title": "Polar coordinate transformations for machine-learning-based dark matter subhalo detection in strong gravitational lenses",
  "title_text": "Polar coordinate transformations for machine-learning-based dark matter subhalo detection in strong gravitational lenses",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:17Z",
  "url": "https://research.draconitic.com/paper/197maatzmad7n",
  "venue": "Monthly Notices of the Royal Astronomical Society",
  "versions": []
}