A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes
Abstract
Large-volume neutrino telescopes infer neutrino properties from Cherenkov light, but simulating the transport of billions of photons through highly scattering ice or water is computationally costly. We introduce candela, a differentiable SIREN neural field that learns the photon Green's function of the IceCube Neutrino Observatory, a cubic-kilometer detector embedded in Antarctic glacial ice. Given a point-like energy deposit and sensor, it predicts the expected photon yield and full arrival-time distribution at the sensor. Complete events are simulated by decomposing charged-particle energy deposits into point-like sources and superposing their predicted sensor responses. Trained on Monte-Carlo simulations, candela generates events $50−−100\times$ faster than existing methods, with cost scaling only weakly with neutrino energy. It keeps median yields within 2% of the MC expectation and timing distributions at the MC statistical floor across six photon-count decades. The model also provides end-to-end gradients with respect to event parameters and opens a path toward optimizing scattering-medium properties, which often dominate systematic uncertainties in neutrino telescopes.
Related
- Fast and Differentiable MHD Surrogate for Solar Wind using Neural Operator
- A New Probe of Strongly-Interacting Dark Sector using Neutrino Telescopes
- CURTAIN: Towards a Foundation Model for Neutrino Telescopes
- Missing Light, Misleading Confidence: Optical-Module Readout Loss and Signal Reliability in Neutrino Telescopes
- The contribution of Soviet scientists to the emergence of high-energy neutrino astrophysics: from the Cherenkov effect to underwater and in-ice telescopes
BibTeX
@misc{yu2026differentiable,
title = {{A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes}},
author = {Felix J. Yu and Berthy T. Feng and Nicholas Kamp and Carlos A. Argüelles},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04695},
eprint = {2609.04695},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04695},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes
AU - Felix J. Yu
AU - Berthy T. Feng
AU - Nicholas Kamp
AU - Carlos A. Argüelles
PY - 2026
DA - 2026/09/04
PB - arXiv
DO - 10.48550/arxiv.2609.04695
UR - https://arxiv.org/abs/2609.04695
AB - Large-volume neutrino telescopes infer neutrino properties from Cherenkov light, but simulating the transport of billions of photons through highly scattering ice or water is computationally costly. We introduce candela, a differentiable SIREN neural field that learns the photon Green's function of the IceCube Neutrino Observatory, a cubic-kilometer detector embedded in Antarctic glacial ice. Given a point-like energy deposit and sensor, it predicts the expected photon yield and full arrival-time distribution at the sensor. Complete events are simulated by decomposing charged-particle energy deposits into point-like sources and superposing their predicted sensor responses. Trained on Monte-Carlo simulations, candela generates events $50−−100\times$ faster than existing methods, with cost scaling only weakly with neutrino energy. It keeps median yields within 2% of the MC expectation and timing distributions at the MC statistical floor across six photon-count decades. The model also provides end-to-end gradients with respect to event parameters and opens a path toward optimizing scattering-medium properties, which often dominate systematic uncertainties in neutrino telescopes.
ER -