Self-supervised PINNs solve stellar structure equations data-free by enforcing physical laws and using differentiable surrogates for microphysics, validated against MESA with 3.06% mean relative error.
In2024 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), 1–5 (IEEE, 2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.SR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning the Stellar Structure Equations via Self-supervised Physics-Informed Neural Networks
Self-supervised PINNs solve stellar structure equations data-free by enforcing physical laws and using differentiable surrogates for microphysics, validated against MESA with 3.06% mean relative error.