Skip to Main content Skip to Navigation
Journal articles

Casimir effect with machine learning

Abstract : 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.
Complete list of metadata

Cited literature [57 references]  Display  Hide  Download
Contributor : Maxim Chernodub Connect in order to contact the contributor
Submitted on : Monday, November 9, 2020 - 7:28:42 PM
Last modification on : Tuesday, January 11, 2022 - 5:56:35 PM
Long-term archiving on: : Wednesday, February 10, 2021 - 7:55:35 PM


Files produced by the author(s)




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



Les métriques sont temporairement indisponibles