Application of Artificial Intelligence on the Image Identification of Icing Weather Phenomena

  • Xiaoyu Huang
  • Chengzhi YeEmail author
  • Ronghui Cai
  • Yao Zhang
  • Lianye Liu
  • Chenghao Fu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 550)


Based on field experiments at Nanyue Mountain Meteorological Station and Huaihua National Reference Climatological Station in Hunan Province, the camera images of icing weather phenomena, such as glaze, rime and mixing rime, are collected minutely from January to March in 2018. The convolution neural network technology is employed for modelling and training using the camera images of the icing field experiment at Nanyue station, and the results of identification are examined by the camera images. Furthermore, based on deep learning, the environmental layout requirements of ice accretion image identification are discussed. The main conclusions are as follows. When identifying icing weather phenomena at Nanyue station, the probability of correction (PC) is 99.21%, the false acceptance rate (FAR) is 0.28%, and the probability of omission (PO) is 0.51%. The probability of icing identification increases significantly in the initial stage of ice accretion, while that in the sustained stage is stably around 99.0%, and in the dissipation stage it gradually decreases. False acceptance and omission occur occasionally during the initiation and dissipation stages, the transition period between daytime and night, and the nighttime when the pictures are not clear enough. The test results show that the artificial intelligence identification model established in this paper can extract the key features of icing in different stages of an icing lifetime, and the identification result is good. In addition, the false acceptance and omission can be further eliminated by using the meteorological conditions criteria and judging the consistency of identification. This method can provide important technical support for the automatic observation of icing weather phenomena.


Icing weather phenomena Artificial intelligence Automatic identification 



This research was funded by the Small Business Construction Project of China Meteorological Administration (2018) “Comprehensive Meteorological Observation Intelligent Analysis and Identification System Construction” (QXPG20174022) and Special Project for Capacity Building of Meteorological Forecasting of Hunan Meteorological Bureau (2016-2017) “Meteorological element product improvement based on multi-source data fusion (YBNL16-04)”.


  1. 1.
    China Meterological Administration. The criterion of surface meteorological observation, pp. 21–27. China Meteorological Press, Beijing (2003)Google Scholar
  2. 2.
    Huang, X.Y., Li, Z.X., Li, C., et al.: Analysis on extreme freeze catastrophic weather of Hunan in 2008. Meteorol. Mon. 34(11), 47–53 (2008)Google Scholar
  3. 3.
    Hu, W.D., Yang, K., Huang, X.Y., et al.: Analysis on a severe convection triggered by gust front in Yinchuan with radar data. Plateau Meteorol. 34(5), 1452–1464 (2015)Google Scholar
  4. 4.
    Wang, Z.Y., Ding, Y.H., He, J.H., et al.: An updating analysis of the climate change in China in recent 50 years. ACTA Meteorol. Sin. 62(2), 228–236 (2004)Google Scholar
  5. 5.
    Liang, S.J., Ding, Y.H., Zhao, N., et al.: Analysis of the interdecadal changes of the wintertime surface air temperature over mainland China and regional atmospheric circulation characteristics during 1960–2013. Chin. J. Atmos. Sci. 38(5), 974–992 (2014)Google Scholar
  6. 6.
    Xing, H.Y., Zhang, J.Y., Xu, W., et al.: Development and prospect of automatic meteorological observation technology on the ground. J. Electron. Measur. Instrum. 31(10), 1534–1542 (2017)Google Scholar
  7. 7.
    Ma, S.J., Wu, K.J., Chen, D.D., et al.: Automated present weather observing system and experiment. Meteorol. Mon. 37(9), 1166–1172 (2011)Google Scholar
  8. 8.
    Liu, L.Y., Lan, M.C., Zhu, X.W., et al.: The Comparative analysis of two cloud products of FY2G satellite in Hunan Province. Torrential Rain Disasters 36(2), 164–170 (2017)Google Scholar
  9. 9.
    Hinton, G.E., Osindero, S., TeH, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527 (2006)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(28), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Yu, B.,Li, S., Xu, S.X., et al.: Deep learning: the key to open big data era. J. Eng. Stud. no. 3, 233–243 (2014)Google Scholar
  12. 12.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Chan, C.H., Pang, G.K.H.: Fabric defect detection by Fourier analysis. IEEE Trans. Ind. Appl. 36(5), 1267–1276 (2000)CrossRefGoogle Scholar
  14. 14.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Image net classification with deep convolutional neural networks. In: Proceedings of International Conference on Neural Information Processing System, pp. 1097–1105 (2012)Google Scholar
  15. 15.
    Wang, Z.Y., Zhang, Q., Chen, Y., et al.: Characters of meteorological disasters caused by the extreme synoptic process in early 2008 over China. Clim. Chang. Res. 4(2), 63–67 (2008)Google Scholar
  16. 16.
    Gang, H., Chen, L.J., Jia, X.L., et al.: Analysis of the severe cold surge, ice-snow and frozen disasters in South China during january 2008: II possible climatic causes. Meteorol. Mon. 34(4), 101–106 (2008)Google Scholar
  17. 17.
    Ye, C.Z., Wu, X.Y., Huang, X.Y.: A synoptic analysis of the unprecedented severe event of the consecutive cryogenic freezing rain in Hunan Province. Acta Meteorologica Sin. 67(3), 488–500 (2009)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Xiaoyu Huang
    • 1
  • Chengzhi Ye
    • 2
    Email author
  • Ronghui Cai
    • 2
  • Yao Zhang
    • 3
  • Lianye Liu
    • 2
  • Chenghao Fu
    • 2
  1. 1.National Meteorological CenterBeijingChina
  2. 2.Hunan Meteorological OfficeChangshaChina
  3. 3.Beijing Woquxiu Science and Technology Ltd.BeijingChina

Personalised recommendations