Hydrometeor classification from two-dimensional video disdrometer data

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.

[1]  Gustavo Camps-Valls,et al.  Learning Relevant Image Features With Multiple-Kernel Classification , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Yaolin Liu,et al.  ANALYZING THE SHAPE CHARACTERISTICS OF LAND USE CLASSES IN REMOTE SENSING IMAGERY , 2012 .

[3]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.

[4]  Witold F. Krajewski,et al.  Two-dimensional video disdrometer: A description , 2002 .

[5]  Roland List,et al.  Free-Fall Behavior of Planar Snow Crystals, Conical Graupel and Small Hail , 1971 .

[6]  V. N. Bringi,et al.  Drop Axis Ratios from a 2D Video Disdrometer , 2005 .

[7]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[8]  Monika Hanesch.  Fall velocity and shape of snowflakes , 1999 .

[9]  Wei Qiao,et al.  Support vector machine-based short-term wind power forecasting , 2011, 2011 IEEE/PES Power Systems Conference and Exposition.

[10]  Michael Lehning,et al.  High-Resolution Vertical Profiles of X-Band Polarimetric Radar Observables during Snowfall in the Swiss Alps , 2013 .

[11]  Lorenzo Bruzzone,et al.  Kernel-based methods for hyperspectral image classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Francesca Bovolo,et al.  Supervised change detection in VHR images using contextual information and support vector machines , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[13]  OK emmanuel. goossaert.  Ensemble Classifier for Winter Storm Precipitation in Polarimetric Radar Data , 2008 .

[14]  Brenda Dolan,et al.  A Theory-Based Hydrometeor Identification Algorithm for X-Band Polarimetric Radars , 2009 .

[15]  Stephan Borrmann,et al.  Drop Shapes and Axis Ratio Distributions: Comparison between 2D Video Disdrometer and Wind-Tunnel Measurements , 2009 .

[16]  Alexander V. Ryzhkov,et al.  Analysis of Video Disdrometer and Polarimetric Radar Data to Characterize Rain Microphysics in Oklahoma , 2008 .

[17]  Peter V. Hobbs,et al.  The dimensions and aggregation of ice crystals in natural clouds , 1974 .

[18]  Witold F. Krajewski,et al.  Wind-Induced Error of Raindrop Size Distribution Measurement Using a Two-Dimensional Video Disdrometer , 2000 .

[19]  Guifu Zhang,et al.  Diagnosing the Intercept Parameter for Exponential Raindrop Size Distribution Based on Video Disdrometer Observations: Model Development , 2008 .

[20]  Louisa Nance,et al.  Observations of Precipitation Size and Fall Speed Characteristics within Coexisting Rain and Wet Snow , 2006 .

[21]  Matthew D. Shupe,et al.  A ground‐based multisensor cloud phase classifier , 2007 .

[22]  Jerry M. Straka,et al.  Bulk Hydrometeor Classification and Quantification Using Polarimetric Radar Data: Synthesis of Relations , 2000 .

[23]  David Hudak,et al.  A Methodology to Derive Radar Reflectivity–Liquid Equivalent Snow Rate Relations Using C-Band Radar and a 2D Video Disdrometer , 2010 .

[24]  David Hudak,et al.  On the Possible Use of Copolar Correlation Coefficient for Improving the Drop Size Distribution Estimates at C Band , 2008 .

[25]  K. Beard.  Terminal Velocity and Shape of Cloud and Precipitation Drops Aloft , 1976 .

[26]  Lorenzo Bruzzone,et al.  Kernel methods for remote sensing data analysis , 2009 .

[27]  J. Mercer.  Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .

[28]  Rand E. Feind.  Comparison of Three Classification Methodologies for 2D Probe Hydrometeor Images Obtained from the Armored T-28 Aircraft , 2008 .

[29]  Mikhail Kanevski,et al.  Spatial prediction of monthly wind speeds in complex terrain with adaptive general regression neural networks , 2013 .

[30]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[31]  K. Elmore.  The NSSL Hydrometeor Classification Algorithm in Winter Surface Precipitation: Evaluation and Future Development , 2011 .

[32]  M. Löffler-Mang,et al.  An Optical Disdrometer for Measuring Size and Velocity of Hydrometeors , 2000 .

[33]  J. Delanoë,et al.  Comparison of Airborne In Situ, Airborne Radar–Lidar, and Spaceborne Radar–Lidar Retrievals of Polar Ice Cloud Properties Sampled during the POLARCAT Campaign , 2013 .

[34]  Alexander V. Ryzhkov,et al.  Winter Precipitation Microphysics Characterized by Polarimetric Radar and Video Disdrometer Observations in Central Oklahoma , 2011 .

[35]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[36]  Alexander V. Ryzhkov,et al.  Drop Size Distributions Measured by a 2D Video Disdrometer: Comparison with Dual-Polarization Radar Data , 2001 .

[37]  Joël Jaffrain.  High resolution vertical profiles of polarimetric X-band weather radar observables during snowfall in the Swiss Alps , 2011 .

[38]  Roy Rasmussen,et al.  A Statistical and Physical Description of Hydrometeor Distributions in Colorado Snowstorms Using a Video Disdrometer , 2007 .

[39]  Devis Tuia,et al.  Learning wind fields with multiple kernels , 2011 .

[40]  Frank S. Marzano,et al.  Investigating precipitation microphysics using ground-based microwave remote sensors and disdrometer data , 2010 .

[41]  Dmitri Moisseev,et al.  Recent advances in classification of observations from dual polarization weather radars , 2013 .

[42]  K. Droegemeier,et al.  The Advanced Regional Prediction System (ARPS) – A multi-scale nonhydrostatic atmospheric simulation and prediction model. Part I: Model dynamics and verification , 2000 .