Hydrometeor classification from two-dimensional video disdrometer data

J. Grazioli, D. Tuia, S. Monhart, M. Schneebeli, T. Raupach, A. Berne*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

19 Citations (Scopus)

Abstract

The first hydrometeor classification technique based on two-dimensional video disdrometer (2DVD) data is presented. The method provides an estimate of the dominant hydrometeor type falling over time intervals of 60 s during precipitation, using the statistical behavior of a set of particle descriptors as input, calculated for each particle image. The employed supervised algorithm is a support vector machine (SVM), trained over 60 s precipitation time steps labeled by visual inspection. In this way, eight dominant hydrometeor classes can be discriminated. The algorithm achieved high classification performances, with median overall accuracies (Cohen's K) of 90% (0.88), and with accuracies higher than 84% for each hydrometeor class.

Original languageEnglish
Pages (from-to)2869-2882
Number of pages14
JournalAtmospheric Measurement Techniques
Volume7
Issue number9
DOIs
Publication statusPublished - 9 Sep 2014
Externally publishedYes

Fingerprint Dive into the research topics of 'Hydrometeor classification from two-dimensional video disdrometer data'. Together they form a unique fingerprint.

  • Cite this