Enhancing analytical photon transport in turbid media through physics-guided neural network corrections
Abstract
Analytical methods provide rapid and computationally efficient predictions of light transport in turbid media, making them attractive for real-time and inverse applications. However, their accuracy is limited by the approximations and assumptions used to obtain tractable solutions. On the other hand, Monte Carlo (MC) simulation is widely regarded as the "gold standard" for modeling light transport in turbid media, but its high computational cost limits its use in applications requiring repeated forward evaluations. Here, we introduce a physics-guided residual learning framework that combines the computational efficiency of analytical modeling with the accuracy of MC simulation. As a representative case study, we consider the diffusion approximation (DA), which can exhibit systematic errors under relatively strong absorption, weak scattering, and imperfect boundary treatment. Given the absorption coefficient, scattering coefficient, and anisotropy factor, the corresponding DA prediction is incorporated as a physical prior, while the network learns only the residual between the analytical prediction and the MC reference. Across the evaluated optical-property range, the proposed framework reduces scalar-reflectance RMSE and spatially resolved reflectance RMSLE by factors of approximately 62 and 14, respectively, relative to the diffusion approximation. With only 1\% of the available training data, it achieves approximately 87\% and 93\% lower corresponding errors than a direct neural-network surrogate. These results demonstrate that learning corrections to an analytical physical baseline improves both prediction accuracy and data efficiency.
Related
- Probing quantum anomaly corrections on black hole physics through chaos
- Semi-analytical two-loop QCD corrections to e+e-→ J/ψ+χcJ at B factories
- Semi-analytical two-loop QCD corrections to e+e− → J/ψ + χcJ at B factories
- Underdamped Stochastic Optimal Transport with Landauer boundary conditions: machine learning and analytical solution
- Analytical model for structured light propagation through a turbulent atmosphere
BibTeX
@misc{tang2026enhancing,
title = {{Enhancing analytical photon transport in turbid media through physics-guided neural network corrections}},
author = {Guojun Tang and Paul D. Teal and Alexander Doronin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.26917},
eprint = {2610.26917},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.26917},
}
RIS
TY - UNPB
TI - Enhancing analytical photon transport in turbid media through physics-guided neural network corrections
AU - Guojun Tang
AU - Paul D. Teal
AU - Alexander Doronin
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.26917
UR - https://arxiv.org/abs/2610.26917
AB - Analytical methods provide rapid and computationally efficient predictions of light transport in turbid media, making them attractive for real-time and inverse applications. However, their accuracy is limited by the approximations and assumptions used to obtain tractable solutions. On the other hand, Monte Carlo (MC) simulation is widely regarded as the "gold standard" for modeling light transport in turbid media, but its high computational cost limits its use in applications requiring repeated forward evaluations. Here, we introduce a physics-guided residual learning framework that combines the computational efficiency of analytical modeling with the accuracy of MC simulation. As a representative case study, we consider the diffusion approximation (DA), which can exhibit systematic errors under relatively strong absorption, weak scattering, and imperfect boundary treatment. Given the absorption coefficient, scattering coefficient, and anisotropy factor, the corresponding DA prediction is incorporated as a physical prior, while the network learns only the residual between the analytical prediction and the MC reference. Across the evaluated optical-property range, the proposed framework reduces scalar-reflectance RMSE and spatially resolved reflectance RMSLE by factors of approximately 62 and 14, respectively, relative to the diffusion approximation. With only 1\% of the available training data, it achieves approximately 87\% and 93\% lower corresponding errors than a direct neural-network surrogate. These results demonstrate that learning corrections to an analytical physical baseline improves both prediction accuracy and data efficiency.
ER -