Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field

• URL: http://arxiv.org/abs/2105.09866v1
• Date: Tue, 11 May 2021 10:40:03 GMT
• Title: Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field
• Authors: Zhe Wang and Claude Guet
• Abstract summary: We show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning. We study how the electric potential inside and outside a quasi-cubic particle evolves through a sequence of shapes from a sphere to a cube. The present work's objective is two-fold, first to show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning.
• Score: 4.947248396489835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Solving physics problems for which we know the equations, boundary conditions and symmetries can be done by deep learning. The constraints can be either imposed as terms in a loss function or used to formulate a neural ansatz. In the present case study, we calculate the induced field inside and outside a dielectric cube placed in a uniform electric field, wherein the dielectric mismatch at edges and corners of the cube makes accurate calculations numerically challenging. The electric potential is expressed as an ansatz incorporating neural networks with known leading order behaviors and symmetries and the Laplace's equation is then solved with boundary conditions at the dielectric interface by minimizing a loss function. The loss function ensures that both Laplace's equation and boundary conditions are satisfied everywhere inside a large solution domain. We study how the electric potential inside and outside a quasi-cubic particle evolves through a sequence of shapes from a sphere to a cube. The neural network being differentiable, it is straightforward to calculate the electric field over the whole domain, the induced surface charge distribution and the polarizability. The neural network being retentive, one can efficiently follow how the field changes upon particle's shape or dielectric constant by iterating from any previously converged solution. The present work's objective is two-fold, first to show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning and second to apply the method and study how the induced field and polarizability change when a dielectric particle progressively changes its shape from a sphere to a cube.

Related papers

• Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations [58.130170155147205]
  Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost. Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently. This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules.
  arXiv  Detail & Related papers  (2024-05-23T16:30:51Z)
• Quantum electrodynamics of lossy magnetodielectric samples in vacuum: modified Langevin noise formalism [55.2480439325792]
  We analytically derive the modified Langevin noise formalism from the established canonical quantization of the electromagnetic field in macroscopic media. We prove that each of the two field parts can be expressed in term of particular bosonic operators, which in turn diagonalize the electromagnetic Hamiltonian.
  arXiv  Detail & Related papers  (2024-04-07T14:37:04Z)
• Neural Astrophysical Wind Models [0.0]
  We show that deep neural networks embedded as individual terms in the governing coupled ordinary differential equations (ODEs) can robustly discover both of these physics. We optimize a loss function based on the Mach number, rather than the explicitly solved-for 3 conserved variables, and apply a penalty term towards near-diverging solutions. This work further highlights the feasibility of neural ODEs as a promising discovery tool with mechanistic interpretability for non-linear inverse problems.
  arXiv  Detail & Related papers  (2023-06-20T16:37:57Z)
• Physics-constrained 3D Convolutional Neural Networks for Electrodynamics [77.34726150561087]
  We create a 3D convolutional PCNN to map time-varying current and charge densities J(r,t) and p(r,t) to vector and scalar potentials A(r,t) and V(r,t) We generate electromagnetic fields according to Maxwell's equations: B=curl(A), E=-div(V)-dA/dt.
  arXiv  Detail & Related papers  (2023-01-31T15:51:28Z)
• First principles physics-informed neural network for quantum wavefunctions and eigenvalue surfaces [0.0]
  We propose a neural network to discover parametric eigenvalue and eigenfunction surfaces of quantum systems. We apply our method to solve the hydrogen molecular ion.
  arXiv  Detail & Related papers  (2022-11-08T23:22:42Z)
• On the Su-Schrieffer-Heeger model of electron transport: low-temperature optical conductivity by the Mellin transform [62.997667081978825]
  We describe the low-temperature optical conductivity as a function of frequency for a quantum-mechanical system of electrons that hop along a polymer chain. Our goal is to show vias how the interband conductivity of this system behaves as the smallest energy bandgap tends to close.
  arXiv  Detail & Related papers  (2022-09-26T23:17:39Z)
• Gauge-Invariant Semi-Discrete Wigner Theory [0.0]
  A gauge-invariant Wigner quantum mechanical theory is obtained by applying the Weyl-Stratonovich transform to the von Neumann equation for the density matrix. We derive the evolution equation for the linear electromagnetic case and show that it significantly simplifies for a limit dictated by the long coherence length behavior.
  arXiv  Detail & Related papers  (2022-08-19T08:19:09Z)
• Physics informed neural networks for continuum micromechanics [68.8204255655161]
  Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering. Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization. It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
  arXiv  Detail & Related papers  (2021-10-14T14:05:19Z)
• Quantum Electrodynamics with a Nonmoving Dielectric Sphere: Quantizing Lorenz-Mie Scattering [0.0]
  We quantize the electromagnetic field in the presence of a nonmoving dielectric sphere in vacuum. We specify two useful alternative bases of normalized eigenmodes: spherical eigenmodes and scattering eigenmodes. This work sets the theoretical foundation for describing the quantum interaction between light and the motional, rotational and vibrational degrees of freedom of a dielectric sphere.
  arXiv  Detail & Related papers  (2021-06-15T08:51:47Z)
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks [0.5804039129951741]
  We introduce geometry-aware trial functions in artifical neural networks to improve the training in deep learning for partial differential equations. To exactly impose homogeneous Dirichlet boundary conditions, the trial function is taken as $phi$ multiplied by the PINN approximation. We present numerical solutions for linear and nonlinear boundary-value problems over domains with affine and curved boundaries.
  arXiv  Detail & Related papers  (2021-04-17T03:02:52Z)
• Conditional physics informed neural networks [85.48030573849712]
  We introduce conditional PINNs (physics informed neural networks) for estimating the solution of classes of eigenvalue problems. We show that a single deep neural network can learn the solution of partial differential equations for an entire class of problems.
  arXiv  Detail & Related papers  (2021-04-06T18:29:14Z)

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.