• Azimi, M., 2018: Lecture. Machine Learning and Adaptive Systems, Fort Collins, CO, Colorado State University.

  • Bang, W., K. Kim, L. GyuWon, M. Thurai, P. Kennedy, V. N. Bringi, and B. Notaros, 2016: Microphysical characteristics analysis of three heavy snowfall events from the MASCRAD campaign in Greeley, Colorado, USA. URSI Asia-Pacific Radio Science Conf., Seoul, Korea, IEEE, 1555–1557, https://doi.org/10.1109/URSIAP-RASC.2016.7601356.

  • Besic, N., J. Figueras i Ventura, J. Grazioli, M. Gabella, U. Germann, and A. Berne, 2016: Hydrometeor classification through statistical clustering of polarimetric radar measurements: A semi-supervised approach. Atmos. Meas. Tech., 9, 44254445, https://doi.org/10.5194/amt-9-4425-2016.

    • Search Google Scholar
    • Export Citation
  • Bringi, V. N., P. C. Kennedy, G.-J. Huang, C. Kleinkort, M. Thurai, and B. M. Notaros, 2017: Dual-polarized radar and surface observations of a winter graupel shower with negative Zdr column. J. Appl. Meteor. Climatol., 56, 455470, https://doi.org/10.1175/JAMC-D-16-0197.1.

    • Search Google Scholar
    • Export Citation
  • Chandrasekar, V., R. Keranen, S. Lim, and D. Moisseev, 2013: Recent advances in classification of observations from dual polarization weather radars. Atmos. Res., 119, 97111, https://doi.org/10.1016/j.atmosres.2011.08.014.

    • Search Google Scholar
    • Export Citation
  • Chobanyan, E., N. J. Sekeljiic, A. B. Manic, M. M. Ilic, V. N. Bringi, and B. M. Notaroš, 2015: Efficient and accurate computational electromagnetics approach to precipitation particle scattering analysis based on higher-order method of moments integral equation modeling. J. Atmos. Oceanic Technol., 32, 17451758, https://doi.org/10.1175/JTECH-D-15-0037.1.

    • Search Google Scholar
    • Export Citation
  • Collobert, R., and J. Weston, 2008: A unified architecture for natural language processing: Deep neural networks with multitask learning. Proc. 25th Int. Conf. on Machine Learning, Helsinki, Finland, Association for Computing Machinery, 160–167, https://doi.org/10.1145/1390156.1390177.

  • del-Rio, F., P. Messina, V. Dominguez, and D. Parra, 2018: Do better ImageNet models transfer better... for image recommendation? arXiv, https://arxiv.org/abs/1807.09870.

  • Feind, R. E., 2006: Comparison of three classification methodologies for 2D probe hydrometeor images obtained from the armored T-28 aircraft. Ph.D. thesis, South Dakota School of Mines and Technology, 61 pp.

  • Garrett, T. J., C. Fallgatter, K. Shkurko, and D. Howlett, 2012: Fall speed measurement and high-speed resolution multi-angle photography of hydrometeors in free fall. Atmos. Meas. Tech., 5, 26252633, https://doi.org/10.5194/amt-5-2625-2012.

    • Search Google Scholar
    • Export Citation
  • Goodfellow, I., Y. Bengio, and A. Courville, 2016: Convolutional networks. Deep Learning, MIT Press, 322–359.

  • Grazioli, J., D. Tuia, S. Monhart, M. Schneebeli, T. Raupach, and A. Berne, 2014: Hydrometeor classification from Two-Dimensional Video Disdrometer data. Atmos. Meas. Tech., 7, 28692882, https://doi.org/10.5194/amt-7-2869-2014.

    • Search Google Scholar
    • Export Citation
  • Haykin, S., 2009: Multilayer perceptrons. Neural Networks and Learning Machines, 3rd ed. Pearson, 123–217.

  • He, K., X. Zhang, S. Ren, and J. Sun, 2016: Deep residual learning for image recognition. arXiv, https://arxiv.org/abs/1512.03385.

  • Kennedy, P., M. Thurai, C. Praz, V. N. Bringi, A. Berne, and B. M. Notaros, 2018: Variations in snow crystal riming and ZDR: A case analysis. J. Appl. Meteor. Climatol., 57, 695707, https://doi.org/10.1175/JAMC-D-17-0068.1.

    • Search Google Scholar
    • Export Citation
  • Kim, M. J., 2006: Single scattering parameters of randomly oriented snow particles at microwave frequencies. J. Geophys. Res., 111, D14201, https://doi.org/10.1029/2005JD006892.

    • Search Google Scholar
    • Export Citation
  • Kleinkort, C., G.-J. Huang, V. N. Bringi, and B. M. Notaros, 2017: Visual hull method for realistic 3D particle shape reconstruction based on high-resolution photographs of snowflakes in free fall from multiple views. J. Atmos. Oceanic Technol., 34, 679702, https://doi.org/10.1175/JTECH-D-16-0099.1.

    • Search Google Scholar
    • Export Citation
  • Korolev, A., and B. Sussman, 2000: A technique for habit classification of cloud particles. J. Atmos. Oceanic Technol., 17, 10481057, https://doi.org/10.1175/1520-0426(2000)017<1048:ATFHCO>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Krizhevsky, A., I. Sutskever, and G. E. Hinton, 2012: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, MIT Press, 1097–1105.

  • LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner, 1998: Gradient-based learning applied to document recognition. Proc. IEEE, 86, 22782324, https://doi.org/10.1109/5.726791.

    • Search Google Scholar
    • Export Citation
  • Libbrecht, K. G., 2017: Physical dynamics of ice crystal growth. Annu. Rev. Mat. Res., 47, 271295, https://doi.org/10.1146/annurev-matsci-070616-124135.

    • Search Google Scholar
    • Export Citation
  • Magono, C., and C. W. Lee, 1966: Meteorological classification of natural snow crystals. J. Fac. Sci. Hokkaido Univ., 2, 321335.

  • Mathworks, 2018a: Classify image using GoogleNet. Mathworks, https://www.mathworks.com/help/deeplearning/examples/classify-image-using-googlenet.html.

  • Mathworks, 2018b: Train deep learning network to classify new images. Mathworks, https://www.mathworks.com/help/deeplearning/examples/train-deep-learning-network-to-classify-new-images.html.

  • MathWorks, 2018d: MATLAB and machine learning and deep learning toolbox release. MathWorks, https://www.mathworks.com/solutions/deep-learning.html?s_tid=hp_brand_deeplearning.

  • Minar, M.N., and J. Naher, 2018: Recent advances in deep learning: An overview. arXiv, https://arxiv.org/abs/1807.08169.

  • Mosimann, L., E. Weingartner, and A. Waldvogel, 1994: An analysis of accreted drop sizes and mass on rimed snow crystals. J. Atmos. Sci., 51, 15481558, https://doi.org/10.1175/1520-0469(1994)051<1548:AAOADS>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Murphy, K. P., 2012: Machine Learning, A Probabilistic Perspective. MIT Press, 1067 pp.

  • Newman, A. J., P. A. Kucera, and L. F. Bliven, 2009: Presenting the Snowflake Video Imager (SVI). J. Atmos. Oceanic Technol., 26, 167179, https://doi.org/10.1175/2008JTECHA1148.1.

    • Search Google Scholar
    • Export Citation
  • Notaroš, B. M., and Coauthors, 2016: Accurate characterization of winter precipitation using Multi-Angle Snowflake Camera, visual hull, advanced scattering methods and polarimetric radar. Atmosphere, 7, 81111, https://doi.org/10.3390/atmos7060081.

    • Search Google Scholar
    • Export Citation
  • O’Shea, T. J., J. Corgan, and T. C. Clancy, 2016: Convolutional radio modulation recognition networks. Engineering Applications of Neural Networks, C. Jayne and L. Iliadis, Eds., Springer, 213–226, https://doi.org/10.1007/978-3-319-44188-7_16.

  • Praz, C., R. Yves-Alain, and A. Berne, 2017: Solid hydrometeor classification and riming degree estimation from pictures collected with a Multi-Angle Snowflake Camera. Atmos. Meas. Tech., 10, 13351357, https://doi.org/10.5194/amt-10-1335-2017.

    • Search Google Scholar
    • Export Citation
  • Romanuke, V., 2017: Appropriate number of standard 2 × 2 max pooling layers and their allocation in convolutional neural networks for diverse and heterogeneous datasets. Info. Tech. Manage. Sci., 20, 1219, https://doi.org/10.1515/itms-2017-0002.

    • Search Google Scholar
    • Export Citation
  • Russakovsky, O., and Coauthors, 2015: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision, 115, 211252, https://doi.org/10.1007/s11263-015-0816-y.

    • Search Google Scholar
    • Export Citation
  • Schönhuber, M., G. Lammer, and W. Randeu, 2008: The 2D video disdrometer. Precipitation: Advances in Measurement, Estimation and Prediction, S. Michaelides, Ed., Springer, 3–31.

  • Simonyan, K., and A. Zisserman, 2015: Very deep convolutional networks for large-scale image recognition. arXiv, https://arxiv.org/abs/1409.1556.

  • Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, 2014: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15, 19291958.

    • Search Google Scholar
    • Export Citation
  • Straka, J., D. S. Zrnić, and A. V. Ryzhkov, 2000: Bulk hydrometeor classification and quantification using polarimetric radar data: Synthesis of relations. J. Appl. Meteor., 39, 13411372, https://doi.org/10.1175/1520-0450(2000)039<1341:BHCAQU>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Svozil, D., V. Kvasnička, and J. Pospíchal, 1997: Introduction to multi-layer feed-forward networks. Chemom. Intell. Lab. Syst., 39, 4362, https://doi.org/10.1016/S0169-7439(97)00061-0.

    • Search Google Scholar
    • Export Citation
  • Szegedy, C., and Coauthors, 2015: Going deeper with convolutions. arXiv, https://arxiv.org/abs/1409.4842.

  • Torrey, L., and J. Shavlik, 2009: Transfer learning. Handbook of Research on Machine Learning Applications, IGI Global, 242–264.

  • Tyynelä, J., J. Leinonen, D. Moisseev, and T. Nousiainen, 2011: Radar backscattering from snowflakes: Comparison of fractal, aggregate, and soft spheroid models. J. Atmos. Oceanic Technol., 28, 13651372, https://doi.org/10.1175/JTECH-D-11-00004.1.

    • Search Google Scholar
    • Export Citation
  • Zeiler, M. D., and R. Fergus, 2014: Visualizing and understanding convolutional networks. arXiv, https://arxiv.org/abs/1311.2901.

  • Zhang, G., S. Luchs, A. Ryzhkov, M. Xue, L. Ryzhkova, and Q. Cao, 2011: Winter precipitation microphysics characterized by polarimetric radar and video disdrometer observations in central Oklahoma. J. Appl. Meteor. Climatol., 50, 15581570, https://doi.org/10.1175/2011JAMC2343.1.

    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 501 300 21
PDF Downloads 561 382 32

Method for Classification of Snowflakes Based on Images by a Multi-Angle Snowflake Camera Using Convolutional Neural Networks

View More View Less
  • 1 Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, Colorado
© Get Permissions Rent on DeepDyve
Restricted access

Abstract

Taking advantage of the recent developments in machine learning, we propose an approach to automatic winter hydrometeor classification based on utilization of convolutional neural networks (CNNs). We describe the development, implementation, and evaluation of a method and tool for classification of snowflakes based on geometric characteristics and riming degree, respectively, obtained using CNNs from high-resolution images by a Multi-Angle Snowflake Camera (MASC). These networks are optimal for image classification of winter precipitation particles due to their high accuracy, computational efficiency, automatic feature extraction, and application versatility. They require little initial preparation, enable the use of smaller training sets through transfer learning techniques, come with large supporting communities and a wealth of resources available, and can be applied and operated by nonexperts. We illustrate both the ease of implementation and the usefulness of operation the CNN architecture offers as a tool for researchers and practitioners utilizing in situ optical observational devices. A training dataset containing 1450 MASC images is developed primarily from two storm events in December 2014 and February 2015 in Greeley, Colorado, by visual inspection of recognizable snowflake geometries. Defined geometric classes are aggregate, columnar crystal, planar crystal, small particle, and graupel. The CNN trained on this dataset achieves a mean accuracy of 93.4% and displays excellent generalization (ability to classify new data). In addition, a separate training dataset is developed by sorting snowflakes into three classes and showcasing distinct degrees of riming. The CNN riming degree estimator yields promising initial results but would benefit from larger training sets.

© 2019 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Branislav M. Notaroš, notaros@colostate.edu

Abstract

Taking advantage of the recent developments in machine learning, we propose an approach to automatic winter hydrometeor classification based on utilization of convolutional neural networks (CNNs). We describe the development, implementation, and evaluation of a method and tool for classification of snowflakes based on geometric characteristics and riming degree, respectively, obtained using CNNs from high-resolution images by a Multi-Angle Snowflake Camera (MASC). These networks are optimal for image classification of winter precipitation particles due to their high accuracy, computational efficiency, automatic feature extraction, and application versatility. They require little initial preparation, enable the use of smaller training sets through transfer learning techniques, come with large supporting communities and a wealth of resources available, and can be applied and operated by nonexperts. We illustrate both the ease of implementation and the usefulness of operation the CNN architecture offers as a tool for researchers and practitioners utilizing in situ optical observational devices. A training dataset containing 1450 MASC images is developed primarily from two storm events in December 2014 and February 2015 in Greeley, Colorado, by visual inspection of recognizable snowflake geometries. Defined geometric classes are aggregate, columnar crystal, planar crystal, small particle, and graupel. The CNN trained on this dataset achieves a mean accuracy of 93.4% and displays excellent generalization (ability to classify new data). In addition, a separate training dataset is developed by sorting snowflakes into three classes and showcasing distinct degrees of riming. The CNN riming degree estimator yields promising initial results but would benefit from larger training sets.

© 2019 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Branislav M. Notaroš, notaros@colostate.edu
Save