Decoding the Imprints of Energy-Momentum Squared Gravity in Neutron Stars with Machine Learning Analysis
Abstract
Neutron stars (NSs) provide a unique laboratory for testing gravity in the strong-field regime and for searching for deviations from General Relativity (GR). In this work, we investigate the effects of Energy-Momentum Squared Gravity (EMSG) on NS structure and examine whether its signatures can be identified from observable stellar properties using supervised machine learning (ML). We solve the modified Tolman-Oppenheimer-Volkoff equations for approximately 104 nuclear equations of state (EOSs) for EMSG coupling parameters α={−5.01,−2.50,0,+2.50,+5.01}×10−38 erg−1cm3, and calculate the gravitational mass M, radius R, dimensionless tidal deformability Λ, and fundamental f-mode oscillation frequency for each stellar configuration. Imposing observational constraints on M, R, and Λ, we split our datasets into train and test sets, and we employ Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), and Gaussian Naive Bayes (GNB) to classify the representative sectors α={−5.01,0,+5.01}×10−38 erg−1cm3 using $(M, R,Λ,f)$. The RF classifier performs best, achieving an accuracy of approximately 99.85% with precision, recall, and F1-scores exceeding 99.8%, while KNN also achieves accuracy above 99%. The nearly diagonal confusion matrices demonstrate that the observationally viable NS configurations associated with different EMSG sectors remain highly separable in the multidimensional observable space. Our results show that NS observables retain robust signatures of EMSG even after observational filtering, establishing ML-assisted NS observations as a promising complementary approach for probing modified gravity with current and future multi-messenger observations.
Related
- Energy-momentum-squared gravity: charged quark star solutions with unified interacting matter
- All Quiet on the Vector Front: Scalar Growth and Perturbative Control in Horndeski--Weyl-squared Gravity
- Effect of Gravity-driven Longitudinal Flows in Filaments on Angular Momentum Transport to Embedded Cores
- Decoding RR Lyrae light curves with deep learning for accurate absolute magnitude estimation
- Isotopic imprints of late molecular cloud infall in the outer Solar System
BibTeX
@misc{ghosh2026decoding,
title = {{Decoding the Imprints of Energy-Momentum Squared Gravity in Neutron Stars with Machine Learning Analysis}},
author = {Sayantan Ghosh and Premachand Mahapatra and Dipti Deb},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.09248},
eprint = {2609.09248},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.09248},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Decoding the Imprints of Energy-Momentum Squared Gravity in Neutron Stars with Machine Learning Analysis
AU - Sayantan Ghosh
AU - Premachand Mahapatra
AU - Dipti Deb
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.09248
UR - https://arxiv.org/abs/2609.09248
AB - Neutron stars (NSs) provide a unique laboratory for testing gravity in the strong-field regime and for searching for deviations from General Relativity (GR). In this work, we investigate the effects of Energy-Momentum Squared Gravity (EMSG) on NS structure and examine whether its signatures can be identified from observable stellar properties using supervised machine learning (ML). We solve the modified Tolman-Oppenheimer-Volkoff equations for approximately 10^4 nuclear equations of state (EOSs) for EMSG coupling parameters α={−5.01,−2.50,0,+2.50,+5.01}×10^−38 erg^−1cm^3, and calculate the gravitational mass M, radius R, dimensionless tidal deformability Λ, and fundamental f-mode oscillation frequency for each stellar configuration. Imposing observational constraints on M, R, and Λ, we split our datasets into train and test sets, and we employ Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), and Gaussian Naive Bayes (GNB) to classify the representative sectors α={−5.01,0,+5.01}×10^−38 erg^−1cm^3 using $(M, R,Λ,f)$. The RF classifier performs best, achieving an accuracy of approximately 99.85% with precision, recall, and F1-scores exceeding 99.8%, while KNN also achieves accuracy above 99%. The nearly diagonal confusion matrices demonstrate that the observationally viable NS configurations associated with different EMSG sectors remain highly separable in the multidimensional observable space. Our results show that NS observables retain robust signatures of EMSG even after observational filtering, establishing ML-assisted NS observations as a promising complementary approach for probing modified gravity with current and future multi-messenger observations.
ER -