Articles | Volume 9, issue 9
Atmos. Meas. Tech., 9, 4425–4445, 2016
Atmos. Meas. Tech., 9, 4425–4445, 2016

Research article 08 Sep 2016

Research article | 08 Sep 2016

Hydrometeor classification through statistical clustering of polarimetric radar measurements: a semi-supervised approach

Nikola Besic1,2, Jordi Figueras i Ventura2, Jacopo Grazioli1, Marco Gabella2, Urs Germann2, and Alexis Berne1 Nikola Besic et al.
  • 1Environmental Remote Sensing Laboratory (LTE), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
  • 2Radar, Satellite and Nowcasting Department, MeteoSwiss, Locarno-Monti, Switzerland

Abstract. Polarimetric radar-based hydrometeor classification is the procedure of identifying different types of hydrometeors by exploiting polarimetric radar observations. The main drawback of the existing supervised classification methods, mostly based on fuzzy logic, is a significant dependency on a presumed electromagnetic behaviour of different hydrometeor types. Namely, the results of the classification largely rely upon the quality of scattering simulations. When it comes to the unsupervised approach, it lacks the constraints related to the hydrometeor microphysics. The idea of the proposed method is to compensate for these drawbacks by combining the two approaches in a way that microphysical hypotheses can, to a degree, adjust the content of the classes obtained statistically from the observations. This is done by means of an iterative approach, performed offline, which, in a statistical framework, examines clustered representative polarimetric observations by comparing them to the presumed polarimetric properties of each hydrometeor class. Aside from comparing, a routine alters the content of clusters by encouraging further statistical clustering in case of non-identification. By merging all identified clusters, the multi-dimensional polarimetric signatures of various hydrometeor types are obtained for each of the studied representative datasets, i.e. for each radar system of interest. These are depicted by sets of centroids which are then employed in operational labelling of different hydrometeors. The method has been applied on three C-band datasets, each acquired by different operational radar from the MeteoSwiss Rad4Alp network, as well as on two X-band datasets acquired by two research mobile radars. The results are discussed through a comparative analysis which includes a corresponding supervised and unsupervised approach, emphasising the operational potential of the proposed method.

Short summary
In this paper we propose a novel semi-supervised method for hydrometeor classification, which takes into account both the specificities of acquired polarimetric radar measurements and the presumed electromagnetic behavior of different hydrometeor types. The method has been applied on three datasets, each acquired by different C-band radar from the Swiss network, and on two X-band research radar datasets. The obtained classification is found to be of high quality.