Taming Waves: A Physically-Interpretable Machine Learning Framework for Realizable Control of Wave Dynamics

• URL: http://arxiv.org/abs/2312.09460v1
• Date: Mon, 27 Nov 2023 03:34:28 GMT
• Title: Taming Waves: A Physically-Interpretable Machine Learning Framework for Realizable Control of Wave Dynamics
• Authors: Tristan Shah, Feruza Amirkulova, Stas Tiomkin
• Abstract summary: We introduce an environment designed for the study of the control of acoustic waves by actuated metamaterial designs. We utilize this environment for the development of a novel machine-learning method, based on deep neural networks. Our model is fully interpretable and maps physical constraints and intrinsic properties of the real acoustic environment into its latent representation of information.
• Score: 3.4530027457862
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical constraints and intrinsic properties of wave phenomena such as dissipation, attenuation, reflection, and scattering. In this work, we introduce an environment designed for the study of the control of acoustic waves by actuated metamaterial designs. We utilize this environment for the development of a novel machine-learning method, based on deep neural networks, for efficiently learning the dynamics of an acoustic PDE from samples. Our model is fully interpretable and maps physical constraints and intrinsic properties of the real acoustic environment into its latent representation of information. Within our model we use a trainable perfectly matched layer to explicitly learn the property of acoustic energy dissipation. Our model can be used to predict and control scattered wave energy. The capabilities of our model are demonstrated on an important problem in acoustics, which is the minimization of total scattered energy. Furthermore, we show that the prediction of scattered energy by our model generalizes in time and can be extended to long time horizons. We make our code repository publicly available.

Related papers

• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Wavelet-Enhanced Neural ODE and Graph Attention for Interpretable Energy Forecasting [0.0]
  This paper introduces a neural framework that integrates continuous-time Neural Ordinary Differential Equations (Neural ODEs) and graph attention.<n>It adeptly captures and models diverse, multi-scale temporal dynamics.<n>The model enhances interpretability through SHAP analysis, making it suitable for sustainable energy applications.
  arXiv  Detail & Related papers  (2025-07-14T10:23:18Z)
• Convergence of physics-informed neural networks modeling time-harmonic wave fields [0.0]
  We study 3D room acoustic cases at low frequency, varying the source definition and the number of boundary condition sets.<n>We assess the convergence behavior by looking at the loss landscape of the PINN architecture.<n>The developments are part of an initiative aiming to model the low-frequency behavior of room acoustics, including absorbers.
  arXiv  Detail & Related papers  (2025-05-18T19:12:14Z)
• Mismatch-Robust Underwater Acoustic Localization Using A Differentiable Modular Forward Model [4.2671394819888455]
  We exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based framework to estimate the source location. We introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner.
  arXiv  Detail & Related papers  (2025-03-30T00:12:20Z)
• Data-driven model reconstruction for nonlinear wave dynamics [0.0]
  We present an interpretable machine learning framework for analyzing the nonlinear evolution dynamics of optical wavepackets in complex wave media. We use sparse regression to reduce microscopic discrete lattice models to simpler effective models which can accurately describe the dynamics of the wavepacket envelope. The reconstructed equations accurately reproduce the linear dispersion nonlinear effects including self-steepening and self-focusing.
  arXiv  Detail & Related papers  (2024-11-18T13:17:10Z)
• The Sound of Water: Inferring Physical Properties from Pouring Liquids [85.30865788636386]
  We study the connection between audio-visual observations and the underlying physics of pouring liquids. Our objective is to automatically infer physical properties such as the liquid level, the shape and size of the container, the pouring rate and the time to fill.
  arXiv  Detail & Related papers  (2024-11-18T01:19:37Z)
• Individualized Dosing Dynamics via Neural Eigen Decomposition [51.62933814971523]
  We introduce the Neural Eigen Differential Equation algorithm (NESDE) NESDE provides individualized modeling, tunable generalization to new treatment policies, and fast, continuous, closed-form prediction. We demonstrate the robustness of NESDE in both synthetic and real medical problems, and use the learned dynamics to publish simulated medical gym environments.
  arXiv  Detail & Related papers  (2023-06-24T17:01:51Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs [70.51212431290611]
  Partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics. We propose the Neural Operator with Regularity Structure (NORS) which incorporates the feature vectors for modeling dynamics driven by SPDEs. We conduct experiments on various of SPDEs including the dynamic Phi41 model and the 2d Navier-Stokes equation.
  arXiv  Detail & Related papers  (2022-04-13T08:53:41Z)
• Forced Variational Integrator Networks for Prediction and Control of Mechanical Systems [7.538482310185133]
  We show that forced variational integrator networks (FVIN) architecture allows us to accurately account for energy dissipation and external forcing. This can result in highly-data efficient model-based control and can predict on real non-conservative systems.
  arXiv  Detail & Related papers  (2021-06-05T21:39:09Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)
• QuTiP-BoFiN: A bosonic and fermionic numerical hierarchical-equations-of-motion library with applications in light-harvesting, quantum control, and single-molecule electronics [51.15339237964982]
  "hierarchical equations of motion" (HEOM) is a powerful exact numerical approach to solve the dynamics. It has been extended and applied to problems in solid-state physics, optics, single-molecule electronics, and biological physics. We present a numerical library in Python, integrated with the powerful QuTiP platform, which implements the HEOM for both bosonic and fermionic environments.
  arXiv  Detail & Related papers  (2020-10-21T07:54:56Z)
• Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control [12.691047660244335]
  We introduce a new unsupervised neural network model that learns Lagrangian dynamics from images. The model infers Lagrangian dynamics on generalized coordinates that are simultaneously learned with a coordinate-aware variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-03T20:06:43Z)
• Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning [9.811643357656196]
  We introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. Dissipative SymODEN encodes the port-Hamiltonian dynamics with energy dissipation and external input into the design of its graph and learns the dynamics in a structured way.
  arXiv  Detail & Related papers  (2020-02-20T16:44:10Z)
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control [14.24939133094439]
  We introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system. In particular, we enforce Hamiltonian dynamics with control to learn the underlying dynamics in a transparent way. This framework, by offering interpretable, physically-consistent models for physical systems, opens up new possibilities for synthesizing model-based control strategies.
  arXiv  Detail & Related papers  (2019-09-26T13:13:16Z)

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.