
S2SCAT
is a Python package for computing scattering covariances on the sphere using JAX. It exploits autodiff to provide differentiable transforms, which are also deployable on hardware accelerators (e.g. GPUs and TPUs), leveraging the differentiable and accelerated spherical harmonic and wavelet transforms implemented in S2FFT
and S2WAV
, respectively. Scattering covariances are useful both for field-level generative modelling of complex non-Gaussian textures and for statistical compression of high dimensional field-level data, a key step of e.g. simulation based inference.
Publications
Talks
Geometric deep learning for atmospheric science
Jul 2025
Exeter University
Differentiable and accelerated spherical transforms
Jun 2025
Durham University
Scientific AI in cosmology and beyond
Apr 2025
University of Southampton
Scientific AI in cosmology and beyond
Dec 2024
International School for Advanced Studies (SISSA)
Towards wide-field, field-level simulation-based inference (SBI) for Euclid cosmic shear
Jul 2024
University of Hull