Addressing the ground state of the deuteron by physics-informed neural networks
Abstract
Machine learning techniques have proven to be effective in addressing the structure of atomic nuclei. Physics−Informed Neural Networks (PINNs) are a promising machine learning technique suitable for solving integro-differential problems such as the many-body Schrödinger problem. So far, there has been no demonstration of extracting nuclear eigenstates using such method. Here, we tackle realistic nucleon-nucleon interaction in momentum space, including models with strong high-momentum correlations, and demonstrate highly accurate results for the deuteron. We further provide additional benchmarks in coordinate space. We introduce an expression for the variational energy that enters the loss function, which can be evaluated efficiently within the PINNs framework. Results are in excellent agreement with proven numerical methods, with a relative error between the value of the predicted binding energy by the PINN and the numerical benchmark of the order of 10 − 7 . Our approach paves the way for the exploitation of PINNs to solve more complex atomic nuclei.
Related
- Accelerating noisy variational quantum algorithms with physics-informed denoising networks
- Physics-informed neural networks for soliton solutions and parameter identification of the two-mode Korteweg–de Vries equation
- Lazy training of quantum physics informed neural networks
- Lecture notes on Physics Informed Neural Networks, Neural Operators, and their applications
- Towards Physics-Informed Neural Networks for Stiff Guitar String Vibrations
BibTeX
@article{brevi2026addressing,
title = {{Addressing the ground state of the deuteron by physics-informed neural networks}},
author = {Lorenzo Brevi and Antonio Mandarino and Carlo Barbieri and Enrico Prati},
journal = {Physics Letters B},
year = {2026},
month = oct,
doi = {10.1016/j.physletb.2026.141050},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0370269326009007},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Addressing the ground state of the deuteron by physics-informed neural networks
AU - Lorenzo Brevi
AU - Antonio Mandarino
AU - Carlo Barbieri
AU - Enrico Prati
PY - 2026
DA - 2026/10/30
JO - Physics Letters B
DO - 10.1016/j.physletb.2026.141050
UR - https://linkinghub.elsevier.com/retrieve/pii/S0370269326009007
AB - Machine learning techniques have proven to be effective in addressing the structure of atomic nuclei. Physics−Informed Neural Networks (PINNs) are a promising machine learning technique suitable for solving integro-differential problems such as the many-body Schrödinger problem. So far, there has been no demonstration of extracting nuclear eigenstates using such method. Here, we tackle realistic nucleon-nucleon interaction in momentum space, including models with strong high-momentum correlations, and demonstrate highly accurate results for the deuteron. We further provide additional benchmarks in coordinate space. We introduce an expression for the variational energy that enters the loss function, which can be evaluated efficiently within the PINNs framework. Results are in excellent agreement with proven numerical methods, with a relative error between the value of the predicted binding energy by the PINN and the numerical benchmark of the order of 10 − 7 . Our approach paves the way for the exploitation of PINNs to solve more complex atomic nuclei.
SN - 0370-2693
SN - 1873-2445
ER -