Abstract
Abstract. A data-driven approach to the classification of hydrometeors from measurements collected with polarimetric weather radars is proposed. In a first step, the optimal number of hydrometeor classes (nopt) that can be reliably identified from a large set of polarimetric data is determined. This is done by means of an unsupervised clustering technique guided by criteria related both to data similarity and to spatial smoothness of the classified images. In a second step, the nopt clusters are assigned to the appropriate hydrometeor class by means of human interpretation and comparisons with the output of other classification techniques. The main innovation in the proposed method is the unsupervised part: the hydrometeor classes are not defined a priori, but they are learned from data. The approach is applied to data collected by an X-band polarimetric weather radar during two field campaigns (from which about 50 precipitation events are used in the present study). Seven hydrometeor classes (nopt = 7) have been found in the data set, and they have been identified as light rain (LR), rain (RN), heavy rain (HR), melting snow (MS), ice crystals/small aggregates (CR), aggregates (AG), and rimed-ice particles (RI).
Highlights
Hydrometeor classification (HC) from weather radar data refers to a family of techniques and algorithms that retrieve qualitative information about precipitation: the dominant hydrometeor type within a given sampling volume, where the term “dominant” is used to underline that the actual hydrometeor content is usually a mixture
A novel approach to hydrometeor classification from a polarimetric weather radar was presented in this paper
The novel approach was not based on numerical-scattering simulations
Summary
Hydrometeor classification (HC) from weather radar data refers to a family of techniques and algorithms that retrieve qualitative information about precipitation: the dominant hydrometeor type within a given sampling volume, where the term “dominant” is used to underline that the actual hydrometeor content is usually a mixture. Actual observations are associated (labelled) with the appropriate class according to their degree of similarity with the sets of simulations available This last step is often conducted by means of a fuzzy-logic input–output association Dolan and Rutledge, 2009) or by means of Bayesian (Marzano et al, 2010) or neural network (Liu and Chandrasekar, 2000) techniques In some cases these relations rely entirely on the simulation framework available
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have