Abstract
The airborne two-dimensional stereo (2D-S) optical array probe has been operating for more than 10 yr, accumulating a large amount of cloud particle image data. However, due to the lack of reliable and unbiased classification tools, our ability to extract meaningful morphological information related to cloud microphysical processes is limited. To solve this issue, we propose a novel classification algorithm for 2D-S cloud particle images based on a convolutional neural network (CNN), named CNN-2DS. A 2D-S cloud particle shape dataset was established by using the 2D-S cloud particle images observed from 13 aircraft detection flights in 6 regions of China (Northeast, Northwest, North, East, Central, and South China). This dataset contains 33,300 cloud particle images with 8 types of cloud particle shape (linear, sphere, dendrite, aggregate, graupel, plate, donut, and irregular). The CNN-2DS model was trained and tested based on the established 2D-S dataset. Experimental results show that the CNN-2DS model can accurately identify cloud particles with an average classification accuracy of 97%. Compared with other common classification models [e.g., Vision Transformer (ViT) and Residual Neural Network (ResNet)], the CNN-2DS model is lightweight (few parameters) and fast in calculations, and has the highest classification accuracy. In a word, the proposed CNN-2DS model is effective and reliable for the classification of cloud particles detected by the 2D-S probe.
This is a preview of subscription content, log in via an institution to check access.
References
Atlas, R., J. Mohrmann, J. Finlon, et al., 2021: The University of Washington Ice–Liquid Discriminator (UWILD) improves single-particle phase classifications of hydrometeors within Southern Ocean clouds using machine learning. Atmos. Meas. Tech., 14, 7079–7101, doi: https://doi.org/10.5194/amt-14-7079-2021.
Baumgardner, D., J. L. Brenguier, A. Bucholtz, et al., 2011: Airborne instruments to measure atmospheric aerosol particles, clouds and radiation: A cook’s tour of mature and emerging technology. Atmos. Res., 102, 10–29, doi: https://doi.org/10.1016/j.atmosres.2011.06.021.
Baumgardner, D., S. J. Abel, D. Axisa, et al., 2017: Cloud ice properties: In situ measurement challenges. Meteor. Monogr., 58, 9.1–9.23, doi: https://doi.org/10.1175/AMSMONOGRAPHS-D-16-0011.1.
Castillo-Botón, C., D. Casillas-Pérez, C. Casanova-Mateo, et al., 2022: Machine learning regression and classification methods for fog events prediction. Atmos. Res., 272, 106157, doi: https://doi.org/10.1016/j.atmosres.2022.106157.
Chase, R. J., D. R. Harrison, A. Burke, et al., 2022: A machine learning tutorial for operational meteorology. Part I: Traditional machine learning. Wea. Forecasting, 37, 1509–1529, doi: https://doi.org/10.1175/WAF-D-22-0070.1.
Chen, Q., H. Zhang, X. W. Jing, et al., 2017: Effects of different ice crystal shape assumptions on radiation budget and climate. Acta Meteor. Sinica, 75, 607–617, doi: https://doi.org/10.11676/qxxb2017.040. (in Chinese)
Dosovitskiy, A., L. Beyer, A. Kolesnikov, et al., 2021: An image is worth 16 × 16 words: Transformers for image recognition at scale. Proceedings of the 9th International Conference on Learning Representations, ICLR, virtual only, doi: https://doi.org/10.48550/arXiv.2010.11929.
Gardoll, S., and O. Boucher, 2022: Classification of tropical cyclone containing images using a convolutional neural network: Performance and sensitivity to the learning dataset. Geosci. Model Dev., 15, 7051–7073, doi: https://doi.org/10.5194/gmd-15-7051-2022.
Grulich, L., R. Weigel, A. Hildebrandt, et al., 2021: Automatic shape detection of ice crystals. J. Comput. Sci., 54, 101429, doi: https://doi.org/10.1016/j.jocs.2021.101429.
Guo, X. L., Z. P. Yu, Z. H. Yang, et al., 2020: Development and application of the high-performance airborne cloud particle imager. Acta Meteor. Sinica, 78, 1050–1064, doi: https://doi.org/10.11676/qxxb2020.059. (in Chinese)
He, K. M., X. Y. Zhang, S. Q. Ren, et al., 2016: Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, 770–778, doi: https://doi.org/10.1109/CVPR.2016.90.
Hicks, A., and B. M. Notaroš, 2019: Method for classification of snowflakes based on images by a multi-angle snowflake camera using convolutional neural networks. J. Atmos. Oceanic Technol., 36, 2267–2282, doi: https://doi.org/10.1175/JTECH-D-19-0055.1.
Holroyd III, E. W., 1987: Some techniques and uses of 2D-C habit classification software for snow particles. J. Atmos. Oceanic Technol., 4, 498–511, doi: https://doi.org/10.1175/1520-0426(1987)004<0498:STAUOC>2.0.CO;2.
Hou, Q. B., D. Q. Zhou, and J. S. Feng, 2021: Coordinate attention for efficient mobile network design. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, 13,713–13,722, doi: https://doi.org/10.1109/CVPR46437.2021.01350.
Hou, T. J., H. C. Lei, Y. J. He, et al., 2021: Aircraft measurements of the microphysical properties of stratiform clouds with embedded convection. Adv. Atmos. Sci., 38, 966–982, doi: https://doi.org/10.1007/s00376-021-0287-8.
Hou, T. J., B. J. Chen, X. Zhou, et al., 2023: Aircraft-based observations of ice concentrations in a midlatitude mixed-phase stratiform cloud system with embedded convection. Atmos. Res., 281, 106471, doi: https://doi.org/10.1016/j.atmosres.2022.106471.
Howard, A., M. Sandler, B. Chen, et al., 2019: Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision, IEEE, Seoul, Korea, 1314–1324, doi: https://doi.org/10.1109/ICCV.2019.00140.
Hu, J., L. Shen, and G. Sun, 2018: Squeeze-and-excitation networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, 7132–7141, doi: https://doi.org/10.1109/CVPR.2018.00745.
Hu, X. F., H. Huang, H. X. Xiao, et al., 2022: Microphysical characteristics of precipitating stratiform clouds in North China revealed by joint observations of an aircraft and a polarimetric radar. J. Atmos. Sci., 79, 2799–2811, doi: https://doi.org/10.1175/JAS-D-21-0248.1.
Huang, M. S., and H. C. Lei, 2020: An improved Holroyd cloud particle habit identification method and its application. Acta Meteor. Sinica, 78, 289–300, doi: https://doi.org/10.11676/qxxb2020.018. (in Chinese)
Hui, L., and M. Belkin, 2020: Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks. Proceedings of the 9th International Conference on Learning Representations, ICLR, virtual only, doi: https://doi.org/10.48550/arXiv.2006.07322.
Hunter, H. E., R. M. Dyer, and M. Glass, 1984: A two-dimensional hydrometeor machine classifier derived from observed data. J. Atmos. Oceanic Technol., 1, 28–36, doi: https://doi.org/10.1175/1520-0426(1984)001<0028:ATDHMC>2.0.CO;2.
Ketkar, N., 2017: Stochastic gradient descent. Deep Learning with Python, N. Ketkar, Ed., Springer, Berkeley, 113–132, doi: https://doi.org/10.1007/978-1-4842-2766-4_8.
Knollenberg, R. G., 1970: The optical array: An alternative to scattering or extinction for airborne particle size determination. J. Appl. Meteor., 9, 86–103, doi: https://doi.org/10.1175/1520-0450(1970)009<0086:TOAAAT>2.0.CO;2.
Korolev, A., 2007: Reconstruction of the sizes of spherical particles from their shadow images. Part I: Theoretical considerations. J. Atmos. Oceanic Technol., 24, 376–389, doi: https://doi.org/10.1175/jtech1980.1.
Korolev, A., and B. Sussman, 2000: A technique for habit classification of cloud particles. J. Atmos. Oceanic Technol., 17, 1048–1057, doi: https://doi.org/10.1175/1520-0426(2000)017<1048:ATFHCO>2.0.CO;2.
Lawson, R. P., 2011: Effects of ice particles shattering on the 2D-S probe. Atmos. Meas. Tech., 4, 1361–1381, doi: https://doi.org/10.5194/amt-4-1361-2011.
Lawson, R. P., B. A. Baker, P. Zmarzly, et al., 2006: Microphysical and optical properties of atmospheric ice crystals at South Pole Station. J. Appl. Meteor. Climatol., 45, 1505–1524, doi: https://doi.org/10.1175/JAM2421.1.
Li, J., and J. T. Mao, 2006: Simulation about influences of ice property changes on cirrus radiative properties. Meteor. Mon., 32, 9–13, doi: https://doi.org/10.3969/j.issn.1000-0526.2006.02.002. (in Chinese)
Liao, M. Y., J. Duan, R. Zhang, et al., 2021: A hypergraph-embedded convolutional neural network for ice crystal particle habit classification. Intell. Autom. Soft Comput., 29, 787–801, doi: https://doi.org/10.32604/iasc.2021.018190.
Lindqvist, H., K. Muinonen, T. Nousiainen, et al., 2012: Ice-cloud particle habit classification using principal components. J. Geophys. Res. Atmos., 117, D16206, doi: https://doi.org/10.1029/2012JD017573.
Liu, Z., Y. T. Lin, Y. Cao, et al., 2021: Swin transformer: Hierarchical vision transformer using shifted windows. 2021 IEEE/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, 9992–10,002, doi: https://doi.org/10.1109/ICCV48922.2021.00986.
Matus, A. V., and T. S. L’Ecuyer, 2017: The role of cloud phase in Earth’s radiation budget. J. Geophys. Res. Atmos., 122, 2559–2578, doi: https://doi.org/10.1002/2016JD025951.
Ouallouche, F., K. Labadi, Y. Mohia, et al., 2023: Artificial intelligence for satellite image processing: Application to rainfall estimation. Intelligent Systems and Applications: Select Proceedings of ICISA 2022, A. J. Kulkarni, S. Mirjalili, and S. K. Udgata, Eds., Springer, Singapore, 165–174, doi: https://doi.org/10.1007/978-981-19-6581-4_14.
Praz, C., S. Ding, G. M. McFarquhar, et al., 2018: A versatile method for ice particle habit classification using airborne imaging probe data. J. Geophys. Res. Atmos., 123, 13,472–13,495, doi: https://doi.org/10.1029/2018JD029163.
Przybylo, V. M., K. J. Sulia, C. G. Schmitt, et al., 2022: Classification of cloud particle imagery from aircraft platforms using convolutional neural networks. J. Atmos. Oceanic Technol., 39, 405–424, doi: https://doi.org/10.1175/JTECH-D-21-0094.1.
Ramanathan, V., P. J. Crutzen, J. T. Kiehl, et al., 2001: Aerosols, climate, and the hydrological cycle. Science, 294, 2119–2124, doi: https://doi.org/10.1126/science.1064034.
Simonyan, K., and A. Zisserman, 2015: Very deep convolutional networks for large-scale image recognition. Proc. of the 3rd International Conference on Learning Representations, ICLR, San Diego, USA, doi: https://doi.org/10.48550/arXiv.1409.1556.
Stubenrauch, C. J., W. B. Rossow, S. Kinne, et al., 2013: Assessment of global cloud datasets from satellites: Project and database initiated by the GEWEX Radiation Panel. Bull. Amer. Meteor. Soc., 94, 1031–1049, doi: https://doi.org/10.1175/BAMS-D-12-00117.1.
Tan, M. X., and Q. V. Le, 2019: EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, ICML, Long Beach, USA, 6105–6114, doi: https://doi.org/10.48550/arXiv.1905.11946.
Touloupas, G., A. Lauber, J. Henneberger, et al., 2020: A convolutional neural network for classifying cloud particles recorded by imaging probes. Atmos. Meas. Tech., 13, 2219–2239, doi: https://doi.org/10.5194/amt-13-2219-2020.
Wang, L., C. C. Li, Z. L. Zhao, et al., 2014: Application of 2D habit classification in cloud microphysics analysis. Chinese J. Atmos. Sci., 38, 201–212, doi: https://doi.org/10.3878/j.issn.1006-9895.2013.12176. (in Chinese)
Wang, Y., R. Y. Kong, M. Cai, et al., 2023: High small ice concentration in stratiform clouds over Eastern China based on aircraft observations: Habit properties and potential roles of secondary ice production. Atmos. Res., 281, 106495, doi: https://doi.org/10.1016/j.atmosres.2022.106495.
Wu, H. P., B. Xiao, N. Codella, et al., 2021: CvT: Introducing convolutions to vision transformers. 2021 IEEE/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, 22–31, doi: https://doi.org/10.1109/ICCV48922.2021.00009.
Wu, W., and G. M. McFarquhar, 2016: On the impacts of different definitions of maximum dimension for nonspherical particles recorded by 2D imaging probes. J. Atmos. Oceanic Technol., 33, 1057–1072, doi: https://doi.org/10.1175/jtech-d-15-0177.1.
Wu, Z. P., S. Liu, D. L. Zhao, et al., 2020: Neural network classification of ice-crystal images observed by an airborne cloud imaging probe. Atmos. Ocean, 58, 303–315, doi: https://doi.org/10.1080/07055900.2020.1843393.
Xiao, H. X., F. Zhang, Q. S. He, et al., 2019: Classification of ice crystal habits observed from airborne cloud particle imager by deep transfer learning. Earth Space Sci., 6, 1877–1886, doi: https://doi.org/10.1029/2019EA000636.
Xiao, H. X., F. Zhang, Z. Shen, et al., 2021: Classification of weather phenomenon from images by using deep convolutional neural network. Earth Space. Sci., 8, e2020EA001604, doi: https://doi.org/10.1029/2020EA001604.
Zagoruyko, S., and N. Komodakis, 2016: Wide residual networks. Proceedings of the British Machine Vision Conference 2016, BMVC, York, UK, 1–15, doi: https://doi.org/10.48550/arXiv.1605.07146.
Zhang, R., H. Y. Li, X. Zhou, et al., 2021: Shape recognition of DMT airborne cloud particle images and its application. J. Appl. Meteor. Sci., 32, 735–747, doi: https://doi.org/10.11898/1001-7313.20210608. (in Chinese)
Zhang, Z. Z., H. Zhang, L. Zhao, et al., 2021: Nested hierarchical transformer: Towards accurate, data-efficient and interpretable visual understanding. Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, virtual only, doi: https://doi.org/10.48550/arXiv.2105.12723.
Zhou, Y. Q., C. Song, M. Cai, et al., 2022: Identifying supercooled liquid water in cloud based on airborne observations: Correlation of cloud particle number concentration with icing probability and proportion of spherical particles. J. Meteor. Res., 36, 574–585, doi: https://doi.org/10.1007/s13351-022-1064-z.
Zhou, Z. H., 2016: Machine Learning. Tsinghua University Press, Beijing, 448 pp, doi: https://doi.org/10.1007/978-981-15-19-67-3. (in Chinese)
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Key Research and Development Program of China (2019YFC1510301), Key Innovation Team Fund of the China Meteorological Administration (CMA2022ZD10), and Basic Research Fund of the Chinese Academy of Meteorological Sciences (2021Y010).
Rights and permissions
About this article
Cite this article
Zhang, R., Xiao, H., Gao, Y. et al. Shape Classification of Cloud Particles Recorded by the 2D-S Imaging Probe Using a Convolutional Neural Network. J Meteorol Res 37, 521–535 (2023). https://doi.org/10.1007/s13351-023-2146-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13351-023-2146-2