Avanços e perspectivas na pesquisa sobre estimativa da intensidade de ciclones tropicais baseada em aprendizado profundo

  • role: First author第一作者
  • Affiliation:

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    University of Chinese Academy of Sciences, Beijing 100049, China

  • Email:zhaozhitao19@ucas.ac.cn
  • Introduction:赵智韬,研究方向为遥感图像处理。E-mail: zhaozhitao19@ucas.ac.cn
ZHAO Zhitao12,  
  • role: Corresponding author通信作者
  • Affiliation:

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email:zhangzheng2035@163.com
  • Introduction:张正,研究方向为人工智能的遥感应用。E-mail: zhangzheng2035@163.com
ZHANG Zheng1*,  
  • Affiliation:

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

CUI Linli3,  
  • Affiliation:

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

TANG Ping1,  
  • Affiliation:

    Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China

WANG Qiao4

Resumo

Nos últimos anos, com o desenvolvimento do aprendizado profundo, tecnologias de sensoriamento remoto e outras disciplinas relacionadas, a pesquisa sobre a estimativa da intensidade de ciclones tropicais avançou rapidamente. As fontes de dados utilizadas para a estimativa da intensidade de ciclones tropicais foram gradualmente ampliadas de dados de um único canal para dados multicanais, incluindo infravermelho, vapor d'água, micro-ondas, entre outros; os métodos de estimativa também evoluíram de métodos subjetivos baseados na extração manual de características para métodos objetivos automatizados baseados em modelos de aprendizado profundo. Este artigo resume e revisa sistematicamente os avanços recentes na pesquisa sobre a estimativa da intensidade de ciclones tropicais baseada em aprendizado profundo e faz uma breve síntese das fontes de dados e conjuntos de dados utilizados pelos algoritmos. Por fim, são propostas direções futuras de pesquisa para a estimativa da intensidade de ciclones tropicais: por um lado, é necessário se adaptar ao desenvolvimento do big data em sensoriamento remoto, continuar a introduzir novas teorias e métodos na área de aprendizado profundo e utilizar de forma integrada dados multissource para melhorar a precisão e a capacidade de generalização; por outro lado, é necessário focar nas características meteorológicas e nos mecanismos dos ciclones tropicais para melhorar de forma direcionada os métodos existentes. Além disso, no contexto do big data meteorológico, os métodos de aprendizado profundo terão novas descobertas na área de estimativa da intensidade de ciclones tropicais.

Palavras-chave

ciclones tropicais; aprendizado profundo; estimativa de intensidade; redes convolucionais; dados multicanais

References

  1. 1.
    Chan J C L. 2005. The physics of tropical cyclone motion. Annual Review of Fluid Mechanics, 37(1): 99-128
  2. 2.
    Chen B Y, Chen B F and Chen Y N. 2020a. Real-time tropical cyclone intensity estimation by handling temporally heterogeneous satellite data//Proceedings of the 35th AAAI Conference on Artificial Intelligence. Virtually: AAAI: 14721-14728
  3. 3.
    Chen B Y, Chen B F and Lin H T. 2018a. Rotation-blended CNNs on a new open dataset for tropical cyclone image-to-intensity regression//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London: ACM: 90-99
  4. 4.
    Chen L S. 2006. The evolution on research and operational forecasting techniques of tropical cyclones. Journal of Applied Meteorological Science, 17(6): 672-681
  5. 5.
    Chen L S and Xu Y L. 2017. Review of typhoon very heavy rainfall in China. Meteorological and Environmental Sciences, 40(1): 3-10
  6. 6.
    Chen R, Zhang W M and Wang X. 2020b. Machine learning in tropical cyclone forecast modeling: a review. Atmosphere, 11(7): 676
  7. 7.
    Chen Z and Yu X X. 2021. A novel tensor network for tropical cyclone intensity estimation. IEEE Transactions on Geoscience and Remote Sensing, 59(4): 3226-3243
  8. 8.
    Chen Z, Yu X X, Chen G C and Zhou J F. 2018b. Cyclone intensity estimation using multispectral imagery from the FY-4 satellite. 2018 International Conference on Audio, Language and Image Processing. Shanghai: IEEE: 46-51
  9. 9.
    Combinido J S, Mendoza J R and Aborot J. 2018. A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images//2018 24th International Conference on Pattern Recognition. Beijing: IEEE: 1474-1480
  10. 10.
    Cui L L, Chen Z, Yu X X, Chen G C, Wang X F, Lu Y W and Guo W. 2020. Deep learning estimation of tropical cyclone intensity along the southeast coast of China using FY-4A satellite. Journal of Remote Sensing (in Chinese), 24(7): 842-851
  11. 11.
    Dawood M, Asif A and ul Amir Afsar Minhas F. 2020. Deep-PHURIE: deep learning based hurricane intensity estimation from infrared satellite imagery. Neural Computing and Applications, 32(13): 9009-9017
  12. 12.
    Deng J, Dong W, Socher R, Li L J, Li K and Fei-Fei L. 2009. ImageNet: a large-scale hierarchical image database//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE: 248-255
  13. 13.
    Dvorak V F. 1973. A technique for the analysis and forecasting of tropical cyclone intensities from satellite pictures. Washington: National Environmental Satellite Service
  14. 14.
    Emanuel K. 2004. Tropical cyclone energetics and structure//Atmospheric Turbulence and Mesoscale Meteorology. Cambridge: Cambridge University Press: 165-192
  15. 15.
    Guo Xand Tan Z M, 2017. Tropical cyclone fullness: A new concept for interpreting storm intensity. Geophysical Research Letters, 44(9):4324-4331.
  16. 16.
    Guo Y M, Liu Y, Oerlemans A, Lao S Y, Wu S and Lew M S. 2016. Deep learning for visual understanding: a review. Neurocomputing, 187: 27-48
  17. 17.
    He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 770-778
  18. 18.
    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
  19. 19.
    Lee J, Im J, Cha D H, Park, H and Sim S. 2020. Tropical cyclone intensity estimation using multi-dimensional convolutional neural networks from geostationary satellite data. Remote Sensing, 12(1): 108
  20. 20.
    Liu J, Xu X F and Luo X Y. 2019. Estimation of tropical cyclone intensity using infrared data from a geostationary satellite. Scientific Online Letters on the Atmosphere, 15: 189-192
  21. 21.
    Maskey M, Ramachandran R, Ramasubramanian M, Gurung I, Freitag B, Kaulfus A, Bollinger D, Cecil D J and Miller J. 2020. Deepti: deep-learning-based tropical cyclone intensity estimation system. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 4271-4281
  22. 22.
    Mei W, Pasquero C and Primeau F, 2012. The effect of translation speed upon the intensity of tropical cyclones over the tropical ocean. Geophysical Research Letters, 39(7).
  23. 23.
    Miller J, Maskey M and Berendes T. 2017. Using deep learning for tropical cyclone intensity estimation//American Geophysical Union, Fall Meeting 2017. AGU
  24. 24.
    Ni W C, Stoffelen A, Ren K J and Yang X F. 2022. Tropical cyclone intensity estimation from spaceborne microwave scatterometry and parametric wind models. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 4719-4729
  25. 25.
    Olander T, Wimmers A, Velden C S and Kossin J P. 2021. Investigation of machine learning using satellite-based advanced Dvorak technique analysis parameters to estimate tropical cyclone intensity. Weather and Forecasting, 36(6): 2161-2186
  26. 26.
    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
  27. 27.
    Olander T L and Velden C S. 2009. Tropical cyclone convection and intensity analysis using differenced infrared and water vapor imagery. Weather and Forecasting, 24(6): 1558-1572
  28. 28.
    Olander T L and Velden C S. 2019. The Advanced Dvorak Technique (ADT) for estimating tropical cyclone intensity: update and new capabilities. Weather and Forecasting, 34(4): 905-922
  29. 29.
    Olander T L, Velden C S, Kossin J. 2002. The advanced objective dvorak technique (AODT)-latest upgrades and future directions. 26th Conference on Hurricanes and Tropical Meteorology: 294-295
  30. 30.
    Pradhan R, Aygun R S, Maskey M, Ramachandran R and Cecil D J. 2018. Tropical cyclone intensity estimation using a deep convolutional neural network. IEEE Transactions on Image Processing, 27(2): 692-702
  31. 31.
    Qian Q F, Wang C, Xu Y J, Zhou G B, Liu D and Nie G Z. 2021. A deep learning technique of typhoon intensity estimation. Meteorological Monthly, 47(5): 601-608
  32. 32.
    Ritchie E A, Valliere-Kelley G, Piñeros M F and Tyo J S. 2012. Tropical cyclone intensity estimation in the North Atlantic basin using an improved deviation angle variance technique. Weather and Forecasting, 27(5): 1264-1277
  33. 33.
    Velden C S, Olander T L, Zehr R M. Development of an objective scheme to estimate tropical cyclone intensity from digital geostationary satellite infrared imagery[J]. Weather and Forecasting, 1998, 13(1): 172-186.
  34. 34.
    Wang C, Zheng G, Li X F, Xu Q, Liu B and Zhang J. 2022a. Tropical cyclone intensity estimation from geostationary satellite imagery using deep convolutional neural networks. IEEE Transactions on Geoscience Remote Sensing, 60: 4101416
  35. 35.
    Wang Y Q and Wu C C. 2004. Current understanding of tropical cyclone structure and intensity changes-a review. Meteorology and Atmospheric Physics, 87(4): 257-278
  36. 36.
    Wang Z, Zhao J, Huang H and Wang X Z. 2022b. A review on the application of machine learning methods in tropical cyclone forecasting. Frontiers in Earth Science, 10: 902596
  37. 37.
    Webster P J, Holland G J, Curry J A and Chang H R. 2005. Changes in tropical cyclone number, duration, and intensity in a warming environment. Science, 309(5742): 1844-1846
  38. 38.
    Wimmers A, Velden C and Cossuth J H. 2019. Using deep learning to estimate tropical cyclone intensity from satellite passive microwave imagery. Monthly Weather Review, 147(6): 2261-2282
  39. 39.
    Yu H and Duan Y H. 2002. A statistical analysis on intensity change of tropical cyclone over northwestern pacific. Acta Meteorologica Sinica, 60(6): 680-687
  40. 40.
    Zhang C J, Wang X J, Ma L M and Lu X Q. 2021. Tropical cyclone intensity classification and estimation using infrared satellite images with deep learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 2070-2086
  41. 41.
    Zhang R, Liu Q S and Hang R L. 2020. Tropical cyclone intensity estimation using two-branch convolutional neural network from infrared and water vapor images. IEEE Transactions on Geoscience and Remote Sensing, 58(1): 586-597
  42. 42.
    Zhang Y and Yang Q. 2018. An overview of multi-task learning. National Science Review, 5(1): 30-43
  43. 43.
    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
  44. 44.
    Zhou G B, Qian Q F, Lü X Y, Liu C X and Xu Y J. 2022a. Application of artificial intelligence in typhoon monitoring and forecasting. Journal of Tropical Meteorology, 38(4): 481-491
  45. 45.
    Zhou J, Cui G Q, Hu S D, Zhang Z Y, Yang C, Liu Z Y, Wang L F, Li C C and Sun M S. 2020. Graph neural networks: a review of methods and applications. AI Open, 1: 57-81
  46. 46.
    Zhou M Z and Xu J. 2023. Covariation relationship between tropical cyclone intensity and size change over the Northwest Pacific. Journal of Applied Meteorological Science, 34(4): 463-474
  47. 47.
    Zhuo J Y and Tan Z M. 2021. Physics-augmented deep learning to improve tropical cyclone intensity and size estimation from satellite imagery. Monthly Weather Review, 149(7): 2097-2113

Leia o texto completo

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