An automatic observation-based typing method for EARLINET

We present an automatic aerosolclassification method based solely on European AerosolResearch Lidar Network (EARLINET) intensive optical parameters with the aim of building a network-wide classification tool that could provide near-real-time aerosoltyping information. The presented method depends on a supervised learning technique and makes use of the Mahalanobis distancefunction that relates each un-classified measurement to a pre-defined aerosoltype. As a first step (training phase), a reference dataset is set up consisting of already classified EARLINET data. Using this dataset, we defined eight aerosolclasses: clean continental, polluted continental, dust, mixed dust, polluted dust, mixed marine, smoke, and volcanic ash. The effect of the number of aerosolclasses has been explored, as well as the optimal set of intensive parameters to separate different aerosoltypes. Furthermore, the algorithm is trained with literature particle linear depolarization ratiovalues. As a second step (testing phase), we apply the method to an already classified EARLINET dataset and analyse the results of the comparison to this classified dataset. The predictive accuracy of the automatic classification varies between 59 % (minimum) and 90 % (maximum) from 8 to 4 aerosolclasses, respectively, when evaluated against pre-classified EARLINET lidar. This indicates the potential use of the automatic classification to all network lidar data. Furthermore, the training of the algorithm with particle linear depolarization values found in literature further improves the accuracy: the accuracy range is 69–93 % from 8 (69 %) to 4 (93 %) aerosolclasses, respectively. Additionally, the algorithm has proven to be highly versatile as it adapts to changes in the size of the training dataset and the number of aerosolclasses and classifying parameters. Finally, the low computational time and demand for resources make the algorithm extremely suitable for the implementation within the Single Calculus Chain (SCC), the EARLINET centralised processing suite.