Physics Informed Neural Networks for Simulating Radiative Transfer

Abstract

We propose a novel machine learning algorithm for simulating radiative transfer. Our algorithm is based on physics informed neural networks (PINNs), which are trained by minimizing the residual of the underlying radiative tranfer equations. We present extensive experiments and theoretical error estimates to demonstrate that PINNs provide a very easy to implement, fast, robust and accurate method for simulating radiative transfer. We also present a PINN based algorithm for simulating inverse problems for radiative transfer efficiently.

References in corpus (2)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks

Cited by in corpus (28)

• Simulation of multi-species flow and heat transfer using physics-informed neural networks
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• An overview on deep learning-based approximation methods for partial differential equations
• Unveiling the optimization process of Physics Informed Neural Networks: How accurate and competitive can PINNs be?
• Pre-training strategy for solving evolution equations based on physics-informed neural networks
• Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools
• Complex dynamics on the one-dimensional quantum droplets via time piecewise PINNs
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure
• A deep learning method for multi-material diffusion problems based on physics-informed neural networks
• Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance
• Auxiliary Physics-Informed Neural Networks for Forward, Inverse, and Coupled Radiative Transfer Problems
• Modelling Force-Free Neutron Star Magnetospheres using Physics-Informed Neural Networks
• MieAI: A neural network for calculating optical properties of internally mixed aerosol in atmospheric models
• Neural networks: solving the chemistry of the interstellar medium
• A model-data asymptotic-preserving neural network method based on micro-macro decomposition for gray radiative transfer equations
• SunnyNet: A neural network approach to 3D non-LTE radiative transfer
• An operator preconditioning perspective on training in physics-informed machine learning
• Radiative Transfer as a Bayesian Linear Regression problem
• An approximate Riemann solver approach in Physics-Informed Neural Networks for hyperbolic conservation laws
• On the approximation of functions by tanh neural networks
• Acceleration Potential and Density Profile of Secondary Plasma in the Magnetosphere of Orthogonal Pulsars
• Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs
• Bayesian Reasoning for Physics Informed Neural Networks
• Discovery of Quasi-Integrable Equations from traveling-wave data using the Physics-Informed Neural Networks
• Neural semi-Lagrangian method for high-dimensional advection-diffusion problems
• Towards asteroseismology of neutron stars with physics-informed neural networks
• Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem
• Emissivity Prediction of Functionalized Surfaces Using Artificial Intelligence