Welcome to PhySO’s documentation!
Physical symbolic optimization ( \(\Phi\)-SO ) - A symbolic optimization package built for physics.
Source code: WassimTenachi/PhySO
Documentation: physo.readthedocs.io
Highlights
\(\Phi\)-SO’s symbolic regression module fully leverages physical units constraints in order to infer analytical physical laws from data points, searching in the space of functional forms. For more details see: [Tenachi et al 2023].
\(\Phi\)-SO recovering the equation for a damped harmonic oscillator:
Performances on the standard Feynman benchmark from SRBench comprising 120 expressions from the Feynman Lectures on Physics against popular SR packages.
\(\Phi\)-SO achieves state-of-the-art performance in the presence of noise (exceeding 0.1%) and shows robust performances even in the presence of substantial (10%) noise:
