pint.models.noise_model.square_exponential_kernel

pint.models.noise_model.square_exponential_kernel(nodes: ndarray, log10_sigma: float = -7, log10_ell: float = 2) → ndarray[source]

Squared-exponential (RBF) covariance matrix.

Parameters:

  • nodes (np.ndarray) – 1-D array of evaluation points in seconds.

  • log10_sigma (float) – Log10 of the amplitude.

  • log10_ell (float) – Log10 of the length scale in days.

Returns:

Covariance matrix of shape (len(nodes), len(nodes)).

Return type:

np.ndarray

Notes

The kernel is

\[K(\tau) = \sigma^2 \exp\!\left(-\frac{\tau^2}{2\ell^2}\right) + d\,\delta_{ij}\]

where \(d = (\sigma / 50000)^2\) is a small diagonal regulariser.