浏览全部资源
扫码关注微信
纸质出版日期： 2020-07-07 ，
扫 描 看 全 文
崔林丽,陈昭,于兴兴,陈光琛,王晓峰,陆一闻,郭巍.2020.风云四号卫星东南沿海热带气旋强度深度学习估算.遥感学报,24(7): 842-851
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(Chinese)，24(7): 842-851[DOI：10.11834/jrs.20209124]
热带气旋TC（Tropical Cyclone）是影响中国的一个重要天气系统。TC强度准确估测对台风灾害防御具有至关重要的意义。本文基于第二代静止气象卫星风云四号（FY-4A）多通道扫描成像辐射计AGRI（Advanced Geosynchronous Radiation Imager）资料，建立了台风强度识别的深度卷积神经网络模型CNN（Convolutional Neural Network），对台风强度不同等级和台风中心最大风速进行了试验。结果表明，CNN模型具有良好的高维非线性处理能力和算法稳定性，能对TC强度进行有效估计，不同TC强度等级识别精度均在97%以上，近中心最大风速平均绝对误差MAE（Mean Absolute Error）为1.75 m/s，均方根误差RMSE（Root Mean Square Error）为2.04 m/s。CNN可有效挖掘卫星TC形态的深层信息，对台风强度的定量化估测具有较高的应用前景。
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.
遥感热带气旋FY-4A/AGRI卫星云图深度卷积神经网络强度估测
remote sensingtropical cycloneFY-4/AGRI satellite imageCNNobjective intensity estimation
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 [DOI: 10.1175/1520-0450(2002)041<0461:AAMTET>2.0.CO;2http://dx.doi.org/10.1175/1520-0450(2002)041<0461:AAMTET>2.0.CO;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
戴李杰, 张长江, 薛利成, 马雷鸣, 鲁小琴 . 2018. 红外卫星云图和相关向量机的有眼热带气旋客观定强模型. 遥感学报, 22(4): 581-590） [DOI: 10.11834/jrs.20187234http://dx.doi.org/10.11834/jrs.20187234 ]
Deng L, Yu D and Dahl G E . 2015.Deep belief network for large vocabulary continuous speech recognition.U.S.,20120065976A1
DvorakV F .1975.Tropical cyclone intensity analysis and forecasting from satellite imagery.Monthly Weather Review, 103(5):420-430 [DOI: 10.1175/1520-0493(1975)103<0420:TCIAAF>2.0.CO;2http://dx.doi.org/10.1175/1520-0493(1975)103<0420:TCIAAF>2.0.CO;2 ]
DvorakV F . 1984.Tropical Cyclone Intensity Analysis Using Satellite Data.NOAATechnicalReport NESDIS 11, NOAA, 1-47
DvorakV F . 1995.Tropical Clouds and Cloud Systems Observed in Satellite Imagery: Tropical Cyclones. Workbook Volume 2.Available from NOAA/NESDIS, 5200 Auth Rd., NOAA
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 [DOI: 10.1175/WAF-D-13-00006.1http://dx.doi.org/10.1175/WAF-D-13-00006.1 ]
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 [DOI: 10.1109/CVPR.2014.81http://dx.doi.org/10.1109/CVPR.2014.81 ]
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 [DOI: 10.1175/1520-0477(2000)081<1241:SAOTCU>2.3.CO;2http://dx.doi.org/10.1175/1520-0477(2000)081<1241:SAOTCU>2.3.CO;2 ]
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 [DOI: 10.1175/JAMC-D-14-0112.1http://dx.doi.org/10.1175/JAMC-D-14-0112.1 ]
Krizhevsky A, Sutskever I and Hinton G E . 2012.ImageNet classification with deep convolutional neural networks.Communications of the ACM, 60(6): 84-90[DOI:10.1145/3065386http://dx.doi.org/10.1145/3065386 ]
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
鲁小琴, 雷小途, 余晖, 赵兵科 . 2014. 基于卫星资料进行热带气旋强度客观估算. 应用气象学报, 25(1): 52-58
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 [DOI: 10.1175/WAF975.1http://dx.doi.org/10.1175/WAF975.1 ]
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 [DOI: 10.1109/tgrs.2008.2000819http://dx.doi.org/10.1109/tgrs.2008.2000819 ]
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 [DOI: 10.1175/WAF-D-10-05062.1http://dx.doi.org/10.1175/WAF-D-10-05062.1 ]
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
钱金芳, 张长江, 杨波, 马雷鸣 . 2015. 红外云图的台风内核风速建模的RBFNN和PDE方法. 红外与激光工程, 44(2): 438-444 [DOI: 10.3969/j.issn.1007-2276.2015.02.007http://dx.doi.org/10.3969/j.issn.1007-2276.2015.02.007 ]
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 [DOI: 10.1175/WAF-D-13-00133.1http://dx.doi.org/10.1175/WAF-D-13-00133.1 ]
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 [DOI: 10.1109/LGRS.2014.2334561http://dx.doi.org/10.1109/LGRS.2014.2334561 ]
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[DOI: 10.1175/1520-0434(1998)013<0172:doaost>2.0.co;2http://dx.doi.org/10.1175/1520-0434(1998)013<0172:doaost>2.0.co;2 ]
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
王瑾, 江吉喜 . 2005. 热带气旋强度的卫星探测客观估计方法研究. 应用气象学报, 16(3): 283-292 [DOI:10.3969/j.issn.1001-7313.2005.03.002http://dx.doi.org/10.3969/j.issn.1001-7313.2005.03.002 ]
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
王新, 郭强 . 2014. 基于FY-2E卫星CIBLE定标结果的台风客观定强效果评估. 红外与毫米波学报, 33(4): 442-449 [DOI: 10.3724/SP.J.1010.2014.00442http://dx.doi.org/10.3724/SP.J.1010.2014.00442 ]
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 [DOI: 10.1175/WAF-D-14-00113.1http://dx.doi.org/10.1175/WAF-D-14-00113.1 ]
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
许映龙, 张玲, 向纯怡 . 2015. 台风定强技术及业务应用—以Dvorak技术为例. 气象科技进展, 5(4): 22-34 [DOI: 10.3969/j.issn.2095-1973.2015.04.003http://dx.doi.org/10.3969/j.issn.2095-1973.2015.04.003 ]
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 [DOI: 10.2151/jmsj.84.519http://dx.doi.org/10.2151/jmsj.84.519 ]
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
袁猛, 钟玮, 武帅, 田路通 . 2018. 利用偏角方差技术分析2015年西北太平洋超强台风全生命史过程演变特征. 气候变化研究快报, 7(6): 430-441 [DOI: 10.12677/CCRL.2018.76047http://dx.doi.org/10.12677/CCRL.2018.76047 ]
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 [DOI: 10.3390/atmos7030040http://dx.doi.org/10.3390/atmos7030040 ]
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
郑远攀, 李广阳, 李晔 . 2019. 深度学习在图像识别中的应用研究综述. 计算机工程与应用, 55(12): 20-36 [DOI: 10.3778/j.issn.1002-8331.1903-0031http://dx.doi.org/10.3778/j.issn.1002-8331.1903-0031 ]
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
郑峰, 曾智华, 雷小途, 陈联寿 . 2016. 中国近海突然增强台风统计分析. 高原气象, 35(1): 198-210 [DOI: 10.7522/j.issn.1000-0534.2014.00148http://dx.doi.org/10.7522/j.issn.1000-0534.2014.00148 ]
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 [DOI: 10.1109/TGRS.2017.2675902http://dx.doi.org/10.1109/TGRS.2017.2675902 ]
Zhou F Y, Jin L P and Dong J . 2017.Review of convolutional neural network. Chinese Journal of Computers, 40(6): 1229-1251
周飞燕, 金林鹏, 董军 . 2017. 卷积神经网络研究综述. 计算机学报, 40(6): 1229-1251 [DOI: 10.11897/SP.J.1016.2017.01229http://dx.doi.org/10.11897/SP.J.1016.2017.01229 ]
相关作者
相关机构
京公网安备11010802024621