Unified, Verifiable Neural Simulators for Electromagnetic Wave Inverse Problems

• URL: http://arxiv.org/abs/2404.00545v1
• Date: Sun, 31 Mar 2024 03:23:29 GMT
• Title: Unified, Verifiable Neural Simulators for Electromagnetic Wave Inverse Problems
• Authors: Charles Dove, Jatearoon Boondicharern, Laura Waller,
• Abstract summary: We show a single, unified model capable of addressing scattering simulations with thousands of DoFs, of any wavelength, any illumination wavefront, and freeform materials. Our findings demonstrate a path to universal, verifiably accurate neural surrogates for existing scattering simulators.
• Score: 1.6795461001108096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Simulators based on neural networks offer a path to orders-of-magnitude faster electromagnetic wave simulations. Existing models, however, only address narrowly tailored classes of problems and only scale to systems of a few dozen degrees of freedom (DoFs). Here, we demonstrate a single, unified model capable of addressing scattering simulations with thousands of DoFs, of any wavelength, any illumination wavefront, and freeform materials, within broad configurable bounds. Based on an attentional multi-conditioning strategy, our method also allows non-recurrent supervision on and prediction of intermediate physical states, which provides improved generalization with no additional data-generation cost. Using this O(1)-time intermediate prediction capability, we propose and prove a rigorous, efficiently computable upper bound on prediction error, allowing accuracy guarantees at inference time for all predictions. After training solely on randomized systems, we demonstrate the unified model across a suite of challenging multi-disciplinary inverse problems, finding strong efficacy and speed improvements up to 96% for problems in optical tomography, beam shaping through volumetric random media, and freeform photonic inverse design, with no problem-specific training. Our findings demonstrate a path to universal, verifiably accurate neural surrogates for existing scattering simulators, and our conditioning and training methods are directly applicable to any PDE admitting a time-domain iterative solver.

Related papers

• PIC2O-Sim: A Physics-Inspired Causality-Aware Dynamic Convolutional Neural Operator for Ultra-Fast Photonic Device FDTD Simulation [18.832901682895944]
  We introduce a physics-inspired AI-based prediction framework PIC2OSim for photonic device simulation. We show that PIC2O-Sim provides 51.2% lower roll-out prediction error, 23.5 times fewer parameters than state-of-the-art neural operators.
  arXiv  Detail & Related papers  (2024-06-24T18:15:36Z)
• Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation [80.227864832092]
  Graph neural networks (GNNs) have exhibited exceptional efficacy in a diverse array of applications. The sheer size of large-scale graphs presents a significant challenge to real-time inference with GNNs. We propose an online propagation framework and two novel node-adaptive propagation methods.
  arXiv  Detail & Related papers  (2023-10-17T05:03:00Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Reliable Beamforming at Terahertz Bands: Are Causal Representations the Way Forward? [85.06664206117088]
  Multi-user wireless systems can meet metaverse requirements by utilizing terahertz bandwidth with massive number of antennas. Existing solutions lack proper modeling of channel dynamics, resulting in inaccurate beamforming solutions in high-mobility scenarios. Herein, a dynamic, semantically aware beamforming solution is proposed for the first time, utilizing novel artificial intelligence algorithms in variational causal inference.
  arXiv  Detail & Related papers  (2023-03-14T16:02:46Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models [11.388800758488314]
  We propose a dedicated-temporal neural network based framework for model emulation. The proposed approach can approximate forecasts at fine spatial and temporal resolutions that are often challenging for neural network based approaches. Empirical experiments show good agreement between simulated and emulated firefronts, with an average Jaccard score of 0.76.
  arXiv  Detail & Related papers  (2022-06-17T03:11:18Z)
• Seismic wave propagation and inversion with Neural Operators [7.296366040398878]
  We develop a prototype framework for learning general solutions using a recently developed machine learning paradigm called Neural Operator. A trained Neural Operator can compute a solution in negligible time for any velocity structure or source location. We illustrate the method with the 2D acoustic wave equation and demonstrate the method's applicability to seismic tomography.
  arXiv  Detail & Related papers  (2021-08-11T19:17:39Z)
• Long-time integration of parametric evolution equations with physics-informed DeepONets [0.0]
  We introduce an effective framework for learning infinite-dimensional operators that map random initial conditions to associated PDE solutions within a short time interval. Global long-time predictions across a range of initial conditions can be then obtained by iteratively evaluating the trained model. This introduces a new approach to temporal domain decomposition that is shown to be effective in performing accurate long-time simulations.
  arXiv  Detail & Related papers  (2021-06-09T20:46:17Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)
• EikoNet: Solving the Eikonal equation with Deep Neural Networks [6.735657356113614]
  We propose EikoNet, a deep learning approach to solving the Eikonal equation. Our grid-free approach allows for rapid determination of the travel time between any two points within a continuous 3D domain. The developed approach has important applications to earthquake hypocenter inversion, ray multi-pathing, and tomographic modeling.
  arXiv  Detail & Related papers  (2020-03-25T02:31:53Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.