New dust aerosol identification method for spaceborne lidar measurements

Classification is a critical step in the backscatter lidar data processing to accurately retrieve extinction and backscatter profiles of atmospheric aerosols and clouds. Different schemes, such as the probability distribution functions (PDFs) method, have been used in the cloud and aerosol classification. In this paper, we attempt to use the support vector machine (SVM) to discriminate aerosols from clouds, with a focus on dust aerosol classification in China. To demonstrate the feasibility of the SVM classifier, we chose dust storms that occurred in the Gobi and Taklimakan deserts and observed by the CALIPSO lidar in spring time 2007. The results show that the SVM can correctly identify the dust storms.

Research highlights► Use CALIPSO satellite analyzed the dust storms which happened in China. ► Use the support vector machines classified the cloud layer and dust aerosol. ► Import MODIS and CPR as the auxiliary facilities to validate the classification. ► SVM can classify the dense dust aerosol and cloud successfully.