Homogeneous temperature data record derived from 13 years of IASI data using an artificial neural network

Bouillon et al. (2022) recently designed a neural network to retrieve atmospheric temperatures from the IASI radiance data. This new temperature data record is validated against other datasets and a good agreement is shown. Trends were computed from this new temperature dataset over the 2008–2020 period. A general warming of the troposphere, more important at the poles, was found. In the stratosphere, the paper found that temperatures globally decrease everywhere, except at the South Pole as a result of the ozone layer recovery and a sudden stratospheric warming in 2019. The cooling is more pronounced in the equatorial upper stratosphere.