Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Neural network approaches for quantum energy level prediction

Khalili Golmankhaneh, Alireza ; Pasechnik, Roman LU and Jørgensen, Palle E.T. (2026) In Soft Computing 30(6). p.4379-4385
Abstract

Artificial neural networks (ANNs) are employed to predict the energy levels of quantum systems, including the hydrogen atom, the harmonic oscillator, and the particle in a box, using various activation functions. The results demonstrate that the choice of activation function significantly influences prediction accuracy. This data-driven framework provides a powerful alternative to explicitly solving the Schrödinger equation, enabling direct estimation of quantum energy spectra from experimental data. The proposed method offers an efficient and flexible tool for the analysis of quantum systems in laboratory settings.

Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial neural networks (ANNs), Harmonic oscillator, Hydrogen atom, Machine learning in quantum physics, Particle in a box, Quantum energy Levels, Schrödinger equation
in
Soft Computing
volume
30
issue
6
pages
7 pages
publisher
Springer Science and Business Media B.V.
external identifiers
  • scopus:105038367614
ISSN
1432-7643
DOI
10.1007/s00500-026-11300-3
language
English
LU publication?
yes
id
5cbb7da3-0a03-4ff7-9ccd-1c362ff036fb
date added to LUP
2026-08-19 11:01:15
date last changed
2026-08-19 11:02:22
@article{5cbb7da3-0a03-4ff7-9ccd-1c362ff036fb,
  abstract     = {{<p>Artificial neural networks (ANNs) are employed to predict the energy levels of quantum systems, including the hydrogen atom, the harmonic oscillator, and the particle in a box, using various activation functions. The results demonstrate that the choice of activation function significantly influences prediction accuracy. This data-driven framework provides a powerful alternative to explicitly solving the Schrödinger equation, enabling direct estimation of quantum energy spectra from experimental data. The proposed method offers an efficient and flexible tool for the analysis of quantum systems in laboratory settings.</p>}},
  author       = {{Khalili Golmankhaneh, Alireza and Pasechnik, Roman and Jørgensen, Palle E.T.}},
  issn         = {{1432-7643}},
  keywords     = {{Artificial neural networks (ANNs); Harmonic oscillator; Hydrogen atom; Machine learning in quantum physics; Particle in a box; Quantum energy Levels; Schrödinger equation}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{4379--4385}},
  publisher    = {{Springer Science and Business Media B.V.}},
  series       = {{Soft Computing}},
  title        = {{Neural network approaches for quantum energy level prediction}},
  url          = {{http://dx.doi.org/10.1007/s00500-026-11300-3}},
  doi          = {{10.1007/s00500-026-11300-3}},
  volume       = {{30}},
  year         = {{2026}},
}