سابِق|تال

Deep learning estimation of tropical cyclone intensity along the southeast coast of China using FY-4A satellite

  • role： First author第一作者
  • Affiliation：

    Shanghai Ecological Forecasting and Remote Sensing Center, Shanghai Meteorological Service, Shanghai 200030, China

  • Email：cllcontact@163.com
  • Introduction：崔林丽，1975年生,女,研究员, 研究方向为卫星遥感理论与应用。E-mail:cllcontact@163.com
CUI Linli1,  
  • Affiliation：

    College of Computer Science and Technology, Donghua University, Shanghai 201620, China

CHEN Zhao2,  
  • Affiliation：

    College of Computer Science and Technology, Donghua University, Shanghai 201620, China

YU Xingxing2,  
  • Affiliation：

    College of Computer Science and Technology, Donghua University, Shanghai 201620, China

CHEN Guangchen2,  
  • Affiliation：

    Shanghai Ecological Forecasting and Remote Sensing Center, Shanghai Meteorological Service, Shanghai 200030, China

WANG Xiaofeng1,  
  • Affiliation：

    Shanghai Ecological Forecasting and Remote Sensing Center, Shanghai Meteorological Service, Shanghai 200030, China

LU Yiwen1,  
  • Affiliation：

    Shanghai Ecological Forecasting and Remote Sensing Center, Shanghai Meteorological Service, Shanghai 200030, China

GUO Wei1

ملخص

A Tropical Cyclone (TC) is one of the most destructive meteorological disasters. The strong winds and heavy precipitation have significant effect on people’slives, property, and social and economic development. Therefore, the accuracy of thepath and intensity prediction of TCs is always an important consideration in meteorological research. However, considering the complexity and variability of typhoon cloud patterns, the existing objective methods are usually based on statistical linear regression.Moreover,they still have deficiencies in expressing the dynamic changes of the complex characteristics of TC cloud patterns. The deep learning algorithm performs well in high-dimensional nonlinear modelingandaccurately identifies the input mode with displacement and slight deformation.This algorithm finds significance in Tropical Cyclone (TC) monitoring with dynamic changes over time. To develop TC intensity estimation technology further in the field of satellite remote sensing, this studyapplied a new machine-learning technology to analyze and to study the TC intensity of FY-4A/AGRI data from China’s second-generation stationary meteorological satellite.First, a deep Convolution Neural Network (CNN) model was used to distinguish effectively and estimate quantitatively the TC intensity level and center wind speed. The images of day and night were placed into the convolution sampling channel of the CNN to obtain and combinesame-size spectral features. Then, multilayer convolution, pooling, nonlinear mapping, and other operations were used to mine the input characteristicsdeeply.Finally, the TC intensity was estimated. The experiment was divided into the TC intensity classification test and the quantitative estimation test of the TC center maximum wind speed. The CNN model was used to convert the recognition of the TC intensity into the pattern recognition of satellite cloud images, which could classify and identify the TC level.The experiment found that the recognition accuracy of the TC intensity was all above 95%regardless of the overall classification accuracy or the respective accuracy of day and night statistics. Compared with k-nearest neighbor, error back-propagation neural network, multiple linear regression, support vector machine, and other classical classification algorithms, itimprovesby 7-16 percentage points. Moreover, the CNN isalso superior to the classical algorithm in terms of classification accuracy. The CNN model comprises two fully connected network layers (each layer has three neurons).The TC wind speed canbequantitatively estimated by prior training samples of the network parameters. Compared with the data of Tropical Cyclone 2017 Yearbook, the mean absolute error of the wind speed was 1.75 m/s, and the root mean square error ofthewind speed was 2.04 m/s, which were lower than the corresponding errors of Deviation Angle Variance Technique (DAVT) by 85.70% and 84.38%.Thus, the CNN algorithm has a high application prospect in the quantitative estimation of typhoon intensity.As the first second-generation Chinese geostationary meteorological satellite to be launched, FY-4A has its advantages of multichannel structure and high spatial and temporal resolution. On the basis of these features, the advantages of the techniquesofthe deep neural network, and theflexible structure of CNN, this study proposesan improved CNN model thatis tailor-made for FY-4A data. The modelhas the capacity to mine the morphological characteristic of typhoons deeply and effectively and achieve high-precision typhoon intensity estimation.Thismodelhas positive research value and application prospect for the quantitative estimation of typhoon intensity.

مفهوم

remote sensing;tropical cyclone;FY-4/AGRI satellite image;CNN;objective intensity estimation

References

  1. 1.
    Bankert R L and Tag P M. 2002. An automated method to estimate tropical cyclone intensity using SSM/I imagery. Journal of Applied Meteorology, 41(5):461-472
  2. 2.
    Dai L J, Zhang C J, Xue L C, Ma L M and Lu X Q. 2018.Eyed tropical cyclone intensity objective estimation model based on infrared satellite image and relevance vector machine. Journal of Remote Sensing, 22(4): 581-590
  3. 3.
    Deng L, Yu D and Dahl G E. 2015.Deep belief network for large vocabulary continuous speech recognition.U.S.,20120065976A1
  4. 4.
    DvorakV F.1975.Tropical cyclone intensity analysis and forecasting from satellite imagery.Monthly Weather Review, 103(5):420-430
  5. 5.
    DvorakV F. 1984.Tropical Cyclone Intensity Analysis Using Satellite Data.NOAATechnicalReport NESDIS11, NOAA, 1-47
  6. 6.
    DvorakV F. 1995.Tropical Clouds and Cloud Systems Observed in Satellite Imagery: Tropical Cyclones. Workbook Volume2.Available from NOAA/NESDIS, 5200 Auth Rd., NOAA
  7. 7.
    Fetanat G, Homaifar A and Knapp K R. 2013.Objective tropical cyclone intensity estimation using analogs of spatial features in satellite data.Weather and Forecasting, 28(6): 1446-1459
  8. 8.
    Girshick R, Donahue J, Darrell T and Malik J. 2014.Rich feature hierarchies for accurate object detection and semantic segmentation//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus: IEEE: 580-587
  9. 9.
    Kidder S Q, Goldberg M D, Zehr R M, DeMaria M, Purdom J F W, Velden C S, Grody N C and Kusselson S J. 2000. Satellite analysis of tropical cyclones using the Advanced Microwave Sounding Unit (AMSU).Bulletin of the American Meteorological Society, 81(6): 1241-1260
  10. 10.
    Knaff J A, Longmore S P, Demaria R T and Molenar D A. 2015.Improved tropical-cyclone flight-level wind estimates using routine infrared satellite reconnaissance. Journal of Applied Meteorology and Climatology, 54(2): 463-478
  11. 11.
    Krizhevsky A, Sutskever I and Hinton G E. 2012.ImageNet classification with deep convolutional neural networks.Communications of the ACM, 60(6): 84-90
  12. 12.
    Lu X Q, Lei X T, Yu H and Zhao B K. 2014.An objective TC intensity estimation method based on satellite data.Journal of Applied Meteorological Science, 25(1): 52-58
  13. 13.
    Olander T L and Velden C S. 2007.The advanced Dvorak technique: continued development of an objective scheme to estimate tropical cyclone intensity using geostationary infrared satellite imagery. Weather and Forecasting, 22(2): 287-298
  14. 14.
    Piñeros M F, Ritchie E A and Tyo J S. 2008.Objective measures of tropical cyclone structure and intensity change from remotely sensed infrared image data. IEEE Transactions on Geoscience and Remote Sensing, 46(11): 3574-3580
  15. 15.
    Piñeros M F, Ritchie E A and Tyo J S. 2011.Estimating tropical cyclone intensity from infrared image data.Weather and Forecasting, 26(5):690-698
  16. 16.
    Qian J F, Zhang C J, Yang B and Ma L M. 2015.Typhoon inner core wind speed modeling method by RBFNN and PDE based on infrared cloud image. Infrared and Laser Engineering, 44(2): 438-444
  17. 17.
    Ritchie E A, Wood K M, Rodríguez-Herrera O G, Piñeros M FandTyo J S. 2014.Satellite-derived tropical cyclone intensity in the North Pacific Ocean using the deviation-angle variance technique.Weather and Forecasting, 29(3): 505-516
  18. 18.
    Rodríguez-Herrera O G, Wood K M, Dolling K P, Black WT, Ritchie E AandTyo J S. 2015. Automatic tracking of Pregenesis tropical disturbances within the deviation angle variance system.IEEEGeoscience and Remote Sensing Letters, 12(2):254-258
  19. 19.
    Velden C S, Olander T L and Zehr R M. 1998.Development of an objective scheme to estimate tropical cyclone intensity from digital geostationary satellite infrared imagery.Weather and Forecasting, 13(1): 172-186
  20. 20.
    Wang J and Jiang J X. 2005.An objective technique for estimating tropical cyclone intensity from geostationary meteorological satellite observation.Journal of Applied Meteorological Science, 16(3): 283-292
  21. 21.
    Wang X and Guo Q. 2014.Performance evaluation of objective tropical cyclone intensity determination with FY-2E/CIBLE results.Journal of Infrared and Millimeter Waves, 33(4): 442-449
  22. 22.
    Wood K M, Rodríguez-Herrera O S, Ritchie E A, Piñeros M F, Hernández I AandTyo J S. 2016. Tropical cyclogenesis detection in the north Pacific using the deviation angle variance technique.Weather and Forecasting, 30(6):1663-1672
  23. 23.
    Xu Y L, Zhang L and Xiang C Y. 2015.Typhoon intensity estimation technique and its operational application: with example of Dvorak technique.Advances in Meteorological Science and Technology, 5(4): 22-34
  24. 24.
    Yu H, Chan J C L and Duan Y H. 2006.Intensity estimation of tropical cyclones over the Western North Pacific with AMSU-A temperature data.Journal of the Meteorological Society of Japan. Ser. II, 84(3): 519-527
  25. 25.
    Yuan M, Zhong W, Wu SandTian L T. 2018.Detecting the intensity evolutions of northwest Pacific super typhoons in 2015 using deviation angle variance technique.Climate Change Research Letters, 7(6): 430-441
  26. 26.
    Zhao Y, Zhao C F, Sun R Y and Wang Z X. 2016.A multiple linear regression model for tropical cyclone intensity estimation from satellite infrared images.Atmosphere, 7(3): 40
  27. 27.
    Zheng Y P, Li G Y and Li Y. 2019.Survey of application of deep learning in image recognition.Computer Engineering and Applications, 55(12): 20-36
  28. 28.
    Zheng F, Zeng Z H, Lei X T and Chen L S. 2016. A statistical study of rapid intensification of typhoons over coastal water of China. Plateau Meteorology, 35(1): 198-210
  29. 29.
    Zhong P, Gong Z Q, Li S TandSchönliebC B. 2017. Learning to diversify deep belief networks for Hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(6): 3516-3530
  30. 30.
    Zhou F Y, Jin L P and Dong J. 2017.Review of convolutional neural network. Chinese Journal of Computers, 40(6): 1229-1251

قراءة النص الكامل

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website