Texture operator for snow particle classification into snowflake and graupel

Nurzynska, Karolina; Kubo, Mamoru; Muramoto, Ken-ichiro

doi:10.1016/j.atmosres.2012.06.013

Cited by 11 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This list includes the 72 descriptors introduced in Praz et al (), 25 descriptors based on the particle corners detection procedure detailed in Lindqvist et al (), and 9 other descriptors implemented for this work. Many of these coefficients had been previously used to describe ice particles in previous studies (e.g., Garrett & Yuter, ; Hogan et al, ; Nurzynska et al, , ; Schmitt & Heymsfield, ). For the sake of brevity, only the 15 descriptors preserved after the feature selection procedure are mentioned here.…”

Section: Methodsmentioning

confidence: 99%

A Versatile Method for Ice Particle Habit Classification Using Airborne Imaging Probe Data

et al. 2018

View full text Add to dashboard Cite

A versatile method to automatically classify ice particle habit from various airborne optical array probes is presented. The classification is achieved using a multinomial logistic regression model. For each airborne probe, the model determines the particle habit (among six classes) based on a large set of geometrical and textural descriptors extracted from the two-dimensional image of a particle. The technique is applied and evaluated using three probes with significantly different specifications: the high volume precipitation spectrometer, the two-dimensional stereo probe, and the cloud particle imager. Performance and robustness of the method are assessed using standard machine learning tools on the basis of thousands of images manually labeled for each of the considered probes. The three classifiers show good performance characterized by overall accuracies and Heidke skill scores above 90%. Depending on the application and user preferences, the classification scheme can be easily adapted. For a more precise output, intraclass subclassification can be achieved in a nested fashion, illustrated here with columnar crystals and aggregates. A comparative study of the classification output obtained with the three probes is presented for two aircraft flight periods selected when the three probes were operating together. Results are globally consistent in term of proportions of habit identified (once blurry and partial images have been automatically discarded). A perfect agreement is not expected as the three considered probes are sensitive to different particle size range.Plain Language Summary An automatic classification method to identify ice particle habit from images is proposed. The technique is applied and evaluated using three airborne probes mounted on research aircraft with significantly different specifications: the high volume precipitation spectrometer, the two-dimensional stereo probe, and the cloud particle imager. The method relies on thousand of images manually classified and advanced machine learning techniques to determine the snow crystal habit among six preset classes. High classification performance is achieved, with accuracies above 90% for each of the considered probes.

show abstract

Section: Methodsmentioning

confidence: 99%

A Versatile Method for Ice Particle Habit Classification Using Airborne Imaging Probe Data

et al. 2018

View full text Add to dashboard Cite

show abstract

“…An advantage of MASC photographs is that particles are photographed from three angles. Additional shape information can be derived from the mean interpixel brightness variability 〈 σ 〉within each image cross section [ Nurzynska et al , ]. The particle complexity χ is defined as

χ = \frac{P}{2 π r_{eq}} ((), 1 + (〈〉, σ))

where r eq is the area equivalent radius of the photographed particle cross section and χ is averaged over triplet views.…”

Section: Measurementsmentioning

confidence: 99%

“…An advantage of MASC photographs is that particles are photographed from three angles. Additional shape information can be derived from the mean interpixel brightness variability ⟨ ⟩ within each image cross section [Nurzynska et al, 2012]. The particle complexity is defined as…”

Section: Effect Of Riming On Size Distributions and Fallspeedmentioning

confidence: 99%

Observed influence of riming, temperature, and turbulence on the fallspeed of solid precipitation

Garrett

Yuter

2014

Geophys. Res. Lett.

121

View full text Add to dashboard Cite

Forecasts of the amount and geographic distribution of snow are highly sensitive to a model's parameterization of hydrometeor fallspeed. Riming is generally thought to lead to particles with a higher mass and terminal velocity. Yet models commonly assume that heavily rimed particles such as graupel have a fixed density and that their settling speed is unaffected by turbulence in storms. Here we show automated measurements of photographed hydrometeor shape and fallspeed using a new instrument placed in Utah's Wasatch Mountain Range. The data show that graupel in low‐turbulence conditions has a size‐dependent fallspeed distribution with a mode near 1 m s−1, a result that is generally consistent with prior observations. However, the distributions are broadened by turbulence and there is a correspondence between particle density and air temperature. In high turbulence and at low temperatures, any sensitivity of fallspeed to particle size disappears.

show abstract

“…Because it is a priori impossible to know exactly what features are relevant to the target concept (i.e., hydrometeor classification), a large set of 72 descriptors derived from the particle size, shape and textural information was introduced. Several of them have already been used for hydrometeor identification purposes in previous works (e.g., Lindqvist et al, 2012;Nurzyńska et al, 2012Nurzyńska et al, , 2013Grazioli et al, 2014;Schmitt and Heymsfield, 2014). As we experienced some issues with the MASC fall speed measuring unit during the campaign in Davos, this parameter was discarded in the proposed methodology.…”

Section: Image Processing and Feature Extractionmentioning

confidence: 99%

“…However, the limited resolution of the device (about 0.2 mm) and the lack of information about the internal structure of the particles because of the binary nature of the images limited those studies to 1 min averaged classification or binary graupel-snowflake classification scheme. Grayscale photographs bring additional information about the texture and surface roughness of the hydrometeors and therefore have the potential to evaluate the riming degree of individual particles (Nurzyńska et al, 2012). A recent investigation by Garrett and Yuter (2014) also showed that the fall speed-size and fall speed-shape relationships were highly uncertain at ground level, the measured fall velocities being strongly affected by local turbulence effects.…”

Section: Introductionmentioning

confidence: 99%

Responses to the reviewers

Berne¹

2017

Preprint

View full text Add to dashboard Cite

A new method to automatically classify solid hydrometeors based on Multi-Angle Snowflake Camera (MASC) images is presented. For each individual image, the method relies on the calculation of a set of geometric and texture-based descriptors to simultaneously identify the hydrometeor type (among six predefined classes), estimate the degree of riming and detect melting snow. The classification tasks are achieved by means of a regularized multinomial logistic regression (MLR) model trained over more than 3000 MASC images manually labeled by visual inspection. In a second step, the probabilistic information provided by the MLR is weighed on the three stereoscopic views of the MASC in order to assign a unique label to each hydrometeor. The accuracy and robustness of the proposed algorithm is evaluated on data collected in the Swiss Alps and in Antarctica. The algorithm achieves high performance, with a hydrometeor-type classification accuracy and Heidke skill score of 95 % and 0.93, respectively. The degree of riming is evaluated by introducing a riming index ranging between zero (no riming) and one (graupel) and characterized by a probable error of 5.5 %. A validation study is conducted through a comparison with an existing classification method based on two-dimensional video disdrometer (2DVD) data and shows that the two methods are consistent.

show abstract

Texture operator for snow particle classification into snowflake and graupel

Cited by 11 publications

References 22 publications

A Versatile Method for Ice Particle Habit Classification Using Airborne Imaging Probe Data

A Versatile Method for Ice Particle Habit Classification Using Airborne Imaging Probe Data

Observed influence of riming, temperature, and turbulence on the fallspeed of solid precipitation

Responses to the reviewers

Contact Info

Product

Resources

About