3 papers
gr-qc2026
APRIL: Auxiliary Physically-Redundant Information in Loss -- A physics-informed framework for parameter estimation with a gravitational-wave case study
Matteo Scialpi, Francesco Di Clemente, Leigh Smith +1
Physics-Informed Neural Networks (PINNs) embed the partial differential equations (PDEs) governing the system under study directly into the training of Neural Networks, ensuring so…
gr-qc2025
PINNGraPE: Physics Informed Neural Network for Gravitational wave Parameter Estimation
Leigh Smith, Matteo Scialpi, Francesco di Clemente +1
Weakly-modelled searches for gravitational waves are essential for ensuring that all potential sources are accounted for in detection efforts, as they make minimal assumptions rega…
physics.comp-ph2025
Explainable autoencoder for neutron star dense matter parameter estimation
Francesco Di Clemente, Matteo Scialpi, MichaÅ Bejger
We present a physics-informed autoencoder designed to encode the equation of state of neutron stars into an interpretable latent space. In particular the input will be encoded in t…