Name: Peter Ukkonen
Type: User
Company: Danish Meteorological Institute
Bio: Recent PhD. Interests: machine learning for weather and climate modeling, code optimization, atmospheric radiation, clouds and convection
Location: Copenhagen
Peter Ukkonen's Projects
Block bootstrap for gridded spatiotemporal data
Julia package for calculating convective indices (e.g. CAPE) from atmospheric sounding data.
optimized ECMWF atmospheric radiation scheme
Fast computation of Area under ROC and Precision-Recall curves
A parallel neural net microframework
RTE+RRTMGP is a set of codes for computing radiative fluxes in planetary atmospheres. This fork uses neural networks for the gas optics computations and optimized code for the radiative transfer.
Website for Scientific Machine Learning community at the Danish Meteorological Institute