Implicit Neural Representation as a Differentiable Surrogate for Photon Propagation in a Monolithic Neutrino Detector

TL;DR

This paper introduces a neural network-based method using SIREN to efficiently model photon propagation in large neutrino detectors, offering scalability, accuracy, and differentiability for improved simulation and data analysis.

Contribution

The paper presents a novel application of implicit neural representations (SIREN) to model photon propagation, reducing memory requirements and enabling scalable, differentiable simulations for neutrino detectors.

Findings

SIREN accurately reproduces photon acceptance maps.

The model uses significantly fewer parameters than traditional look-up tables.

SIREN's differentiability allows for direct optimization on real data.

Abstract

Optical photons are used as signal in a wide variety of particle detectors. Modern neutrino experiments employ hundreds to tens of thousands of photon detectors to observe signal from millions to billions of scintillation photons produced from energy deposition of charged particles. These neutrino detectors are typically large, containing kilotons of target volume, with different optical properties. Modeling individual photon propagation in form of look-up table requires huge computational resources. As the size of a table increases with detector volume for a fixed resolution, this method scales poorly for future larger detectors. Alternative approaches such as fitting a polynomial to the model could address the memory issue, but results in poorer performance. Both look-up table and fitting approaches are prone to discrepancies between the detector simulation and the data collected. We propose a new approach using SIREN, an implicit neural representation with periodic activation functions, to model the look-up table as a 3D scene and reproduces the acceptance map with high accuracy. The number of parameters in our SIREN model is orders of magnitude smaller than the number of voxels in the look-up table. As it models an underlying functional shape, SIREN is scalable to a larger detector. Furthermore, SIREN can successfully learn the spatial gradients of the photon library, providing additional information for downstream applications. Finally, as SIREN is a neural network representation, it is differentiable with respect to its parameters, and therefore tunable via gradient descent. We demonstrate the potential of optimizing SIREN directly on real data, which mitigates the concern of data vs. simulation discrepancies. We further present an application for data reconstruction where SIREN is used to form a likelihood function for photon statistics.