Intercomparisons of liquid water path based on SEVIRI images and gradient boosting regression trees with in-situ observations and satellite-derived products

This contribution presents a technique for the machine-learning-based retrieval of cloud liquid water path. Cloud effects are among the major uncertainties in climate models for estimating and predicting the Earth’s energy budget. The study of cloud processes requires information on cloud physical properties, such as the liquid water path (LWP), which is commonly retrieved from satellite sensors using look-up table approaches. However, the accuracy of LWP varies temporally and spatially, also due to assumptions inherent in any physical retrieval. The aim of this study is to improve the accuracy of LWP and analyze quantitatively the accuracy and its errors. To this end, a statistical LWP retrieval was developed using spectral information from geostationary satellite channels (Meteosat Spinning-Enhanced Visible and Infrared Imager, SEVIRI), and satellite viewing geometry. The machine-learning method chosen is gradient-boosted regression trees (GBRTs), which is an ensemble of decision trees but more effective than traditional tree-based models. This study reports on first results, as well as a comparison between the GBRT-derived LWP estimates and those from the SEVIRI-based products of the Climate Monitoring Satellite Application Facility (CM-SAF, CLAAS-A2), as well as MODIS products. We use case studies for individual in-situ measurement sites in Europe under varying meteorological conditions to determine the factors influencing LWP retrieval quality.