aiqbench analysis
This study applies physics-informed neural networks to solve the long-standing challenge of optimizing scintillator geometries for medical imaging, bypassing traditional non-differentiable Monte Carlo simulations. By enabling end-to-end differentiable optimization of nanophotonic structures, this approach significantly accelerates material design while maintaining rigorous adherence to underlying quantum and particle interaction physics. The work represents a concrete advancement in using machine learning to tackle complex stochastic processes within condensed matter physics applications.
Neural network inverse design of nanophotonic scintillators
arXiv:2606.16309v1 Announce Type: cross Abstract: Scintillators are materials converting high-energy radiation into optical light, essential in a range of technologies such as medical imaging systems and security scanners. Scintillator development and optimization have remained limited by the complexity of their underlying physics, involving stochastic cascades of electron-electron, electron-phonon, and electron-photon interactions. Such processes are typically modeled by non-differentiable Monte Carlo simulations, limiting the applicability of machine learning for scintillator development. Here we present a physics-informed neural network that learns the scintillation cascade process from the incident high-energy particle to photon emission, substantially accelerating scintillator design and optimization. Combining this neural network with photonic simulations enables end-to-end differentiable optimization of the scintillator geometry. This allows us to optimize for arbitrary figures of merit, such as specific target emission patterns.. We demonstrate the concept and characterize it relative to previous approaches by inverse design of nanophotonic scintillators for X-ray imaging.
Abstract:Scintillators are materials converting high-energy radiation into optical light, essential in a range of technologies such as medical imaging systems and security scanners. Scintillator development and optimization have remained limited by the complexity of their underlying physics, involving stochastic cascades of electron-electron, electron-phonon, and electron-photon interactions. Such processes are typically modeled by non-differentiable Monte Carlo simulations, limiting the applicability of machine learning for scintillator development. Here we present a physics-informed neural network that learns the scintillation cascade process from the incident high-energy particle to photon emission, substantially accelerating scintillator design and optimization. Combining this neural network with photonic simulations enables end-to-end differentiable optimization of the scintillator geometry. This allows us to optimize for arbitrary figures of merit, such as specific target emission patterns.. We demonstrate the concept and characterize it relative to previous approaches by inverse design of nanophotonic scintillators for X-ray imaging.
Optics (physics.optics); Quantum Physics (quant-ph)
arXiv:2606.16309 [physics.optics]
(or arXiv:2606.16309v1 [physics.optics] for this version)
https://doi.org/10.48550/arXiv.2606.16309 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 239 words
Related coverage
Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation
arXiv · Sep 7, 2026
Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems
arXiv · Aug 19, 2026
Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture
arXiv · Jun 5, 2026
Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization
arXiv · Aug 17, 2026