Welcome to mlgw_bns’s documentation!
The purpose of the mlgw_bns package is to speed up the generation of gravitational
waveforms for binary neutron star mergers, by training a machine
learning model on effective-one-body waveforms.
The code can be found on the github page.
Contact
Explanation
Usage guides
Package reference
- Model for waveform generation
- Batched, per-mode evaluation (numpy and JAX)
- Single-mode model
- Management of a training and validation dataset
- Multibanding
- Downsampling and interpolation
- Data management
- Principal Component Analysis
- Neural Network
- Hyperparameter Optimization
- Precessing waveforms
- Twisting in the frequency domain
- The orbital phase at the reference frequency
PrecessingModelPrecessingParametersWithExtrinsicEulerAngleseuler_angles()backward_gamma()LEADING_ORDER_MODE_PHASEStwist_modes_frequency_domain()polarizations_from_inertial_modes()twist_coefficients()newtonian_time_to_merger()check_aligned_spin_limit()- Batched, in JAX
- From the LVK spin angles
- The precession dynamics
- Special functions
- Model Validation
- Fixed Dataset Training
- Training at scale