Predictive Modeling of Classical and Quantum Mechanics Using Machine Learning: A Case Study with TensorFlow

In this paper, we present several machine learning approaches for predicting the behavior of both classical and quantum systems. For the classical domain, we model a pendulum subject to multiple forces using both a standard artificial neural network (ANN) and a physics-informed neural network (PINN)...

Full description

Saved in:
Bibliographic Details
Main Author Yazici, Enis
Format Journal Article
LanguageEnglish
Published 08.02.2025
Subjects
Physics - Quantum Physics
Online AccessGet full text

Cover

More Information
Summary:In this paper, we present several machine learning approaches for predicting the behavior of both classical and quantum systems. For the classical domain, we model a pendulum subject to multiple forces using both a standard artificial neural network (ANN) and a physics-informed neural network (PINN). For the quantum domain, we predict the ground state energy of a quantum anharmonic oscillator from discretized potential data using an ANN with convolutional layers (CNN), a long short-term memory (LSTM) network, and a PINN that incorporates the Schrödinger equation. Detailed training outputs and comparisons are provided.
DOI:10.48550/arxiv.2502.05621