Casimir effect with machine learning - Archive ouverte HAL Access content directly
Journal Articles Physical Review Research Year : 2020

Casimir effect with machine learning

(1, 2) , (3) , (2) , (2) , (2)


Vacuum fluctuations of quantum fields between physical objects depend on the shapes, positions, and internal composition of the latter. For objects of arbitrary shapes, even made from idealized materials, the calculation of the associated zero-point (Casimir) energy is an analytically intractable challenge. We propose a new numerical approach to this problem based on machine-learning techniques and illustrate the effectiveness of the method in a (2+1) dimensional scalar field theory. The Casimir energy is first calculated numerically using a Monte-Carlo algorithm for a set of the Dirichlet boundaries of various shapes. Then, a neural network is trained to compute this energy given the Dirichlet domain, treating the latter as black-and-white pixelated images. We show that after the learning phase, the neural network is able to quickly predict the Casimir energy for new boundaries of general shapes with reasonable accuracy.
Fichier principal
Vignette du fichier
1911.07571.pdf (802.43 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02369463 , version 1 (09-11-2020)



Maxim N. Chernodub, Harold Erbin, I. V. Grishmanovskii, V. A. Goy, A. V. Molochkov. Casimir effect with machine learning. Physical Review Research, 2020, 2, pp.033375. ⟨10.1103/PhysRevResearch.2.033375⟩. ⟨hal-02369463⟩
110 View
34 Download



Gmail Facebook Twitter LinkedIn More