Leveraging surface observations and passive satellite retrievals of cloud properties: Applications to cloud type classification and cloud base height retrieval

Clouds are key regulators of the Earths energy budget. Their microphysical and optical properties lead to vastly disparate radiative properties. Retrieving information about clouds is thus crucial to reduce uncerntainties in our estimation of climate change. In this study, we present a common approach to the retrieval of cloud type and cloud base height (CBH), two useful aspects to characterise clouds and their radiative effects.We leverage surface observations of these two cloud characterictics from the network made available by the UK Met Office, linked to satellite retrievals of relevant cloud properties from the MODIS instrument, namely cloud top height, cloud optical thickness and cloud water path. Our approach relies on a convolutional auto-encoder (AE) to project a data cube (dimension of 3 channels, 128 km, 128 km), comprised of the aforementioned cloud properties, to a latent space of lower dimensionality. The latter is then used as predictor for the cloud characteristics of interest.We demonstrate the skill of the developed method by applying it to CBH retrievals. We create a global dataset of retrieved CBH which exhibits accuracy and precision, in particular for low-level cloud bases, achieving a mean absolute error of 379 m and a standard deviation of the absolute error of 328 m. This is also compared to active satellite retrievals and other CBH retrieval methods. The second application focuses on cloud types, defined following the standards of the WMO. With our approach, we retrieve cloud type occurences at a global scale and are able to study their spatial and temporal patterns. We further use the developed method on km-scale global climate model outputs from the ICON model to help diagnostic cloud representation in this new generation of climate models. Lastly, the presented applications illustrate how fusing surface observations and satellite retrievals still constitutes a resourceful approach to study clouds and their properties.