Cosmo-PINN: A Physics-Informed Neural Network for Cosmological Reconstruction
Abstract
We introduce Cosmo-PINN, a Physics-Informed Neural Network for reconstruction of the cosmological theory. In this work we demonstrate the application of the Cosmo-PINN in the reconstruction of the dark energy equation of state parameter $w_{DE}\left( z\right) $ directly from late-time cosmological observations. This framework overcomes the main limitation shared by Gaussian Process and Artificial Neural Network reconstruction approaches, where the recovered solution is driven by the data and it is not necessarily true that it is physically consistent, by embedding the cosmological constraints directly into the loss function as constraints, ensuring that the reconstructed quantities satisfy the physical laws at every point during the training. For the training of the network, we employed background data, and specifically the Baryon Acoustic Oscillation from DESI DR2, the Cosmic Chronometers and three different Supernova compilations, while we simultaneously introduce the cosmological parameters % H0, Ωm0 and rdrag as trained parameters. The reconstruction shows that the trained $w_{DE}\left( z\right) $ crosses the phantom divide around z=0.5 in agreement with the value obtained by the Chevallier-Polarski-Linder model. In the quintessence scenario, the dark energy equation of state parameter is forced to the ΛCDM limit in the past, that is $w_{DE}\left( z\right) \rightarrow -1 $. Finally, we demonstrate the significance of imposing the physical constraints within the loss function by comparing the Cosmo-PINN reconstruction against a purely data-driven neural network with the same architecture.
Related
- C3NN-SBI: Learning hierarchies of N -point statistics from cosmological fields with physics-informed neural networks
- Physics-Informed Neural Networks and Data-Driven Models for GRB X-ray Light-Curve Gap Reconstruction
- Physics Informed Neural Network for Multi-dimensional Turbulent Self-gravitating Flows
- A Physics Informed Neural Network Approach to Decipher Environmental Confinement of Molecular Clouds in the Third Galactic Quadrant
- Reconstructing the generalized Barrow holographic dark energy with physics-informed neural networks
BibTeX
@misc{paliathanasis2026cosmopinn,
title = {{Cosmo-PINN: A Physics-Informed Neural Network for Cosmological Reconstruction}},
author = {Andronikos Paliathanasis},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.30139},
eprint = {2605.30139},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.30139},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Cosmo-PINN: A Physics-Informed Neural Network for Cosmological Reconstruction
AU - Andronikos Paliathanasis
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2605.30139
UR - https://arxiv.org/abs/2605.30139
AB - We introduce Cosmo-PINN, a Physics-Informed Neural Network for reconstruction of the cosmological theory. In this work we demonstrate the application of the Cosmo-PINN in the reconstruction of the dark energy equation of state parameter $w_{DE}\left( z\right) $ directly from late-time cosmological observations. This framework overcomes the main limitation shared by Gaussian Process and Artificial Neural Network reconstruction approaches, where the recovered solution is driven by the data and it is not necessarily true that it is physically consistent, by embedding the cosmological constraints directly into the loss function as constraints, ensuring that the reconstructed quantities satisfy the physical laws at every point during the training. For the training of the network, we employed background data, and specifically the Baryon Acoustic Oscillation from DESI DR2, the Cosmic Chronometers and three different Supernova compilations, while we simultaneously introduce the cosmological parameters % H_0, Ω_m0 and r_drag as trained parameters. The reconstruction shows that the trained $w_{DE}\left( z\right) $ crosses the phantom divide around z=0.5 in agreement with the value obtained by the Chevallier-Polarski-Linder model. In the quintessence scenario, the dark energy equation of state parameter is forced to the ΛCDM limit in the past, that is $w_{DE}\left( z\right) \rightarrow -1 $. Finally, we demonstrate the significance of imposing the physical constraints within the loss function by comparing the Cosmo-PINN reconstruction against a purely data-driven neural network with the same architecture.
ER -