计算机科学 ›› 2020, Vol. 47 ›› Issue (11A): 11-17.doi: 10.11896/jsjkx.201000038
韩瑞1,2, 顾春利3, 李哲4,5, 伍康4, 高峰1, 沈文海1
HAN Rui1,2, GU Chun-li3, LI Zhe4,5, WU Kang4, GAO Feng1, SHEN Wen-hai1
摘要: 台风是一种高影响的强对流天气系统。台风报文资料作为提供台风初值的最初来源,对改进台风预报准确性有一定的帮助,因此做好全球台风的报文快速识别收集工作至关重要。针对现有全球台风报文实时性差、延迟高、报文被动接收的问题,本研究利用MSG,Meteosat-5,MTSAT,GOES-W,GOES-E卫星图像数据,通过训练2006年1月-2020年8月的1 351次全球热带气旋过程,共计8 983张红外卫星图像,基于深度学习算法,提出了一种CNN-typhoon模型,可以对无台风、台风生成、台风最强等3种图像进行识别分类。实验证明:CNN-typhoon模型训练集的识别精度可接近100%,验证集精度高于88.1%;同时将模型代入模拟业务,在一定时段内增加了接近31.0%的报文收集种类,报文收集时效提高了23.5倍。
中图分类号:
[1] DONG L,XU Y L,LYU X Y,et al.Analysis of forecast focuses of binary typhoons Nesata and Haitang [J].Meteor Mon,2020,46(1):29-36. [2] ZHENG Z S,HU C Y,HUANG D M,et al.Research on Transfer Learning Methods for Classification of Typhoon Cloud Image [J].Remote Sensing Technology and Application,2020,35(1):202-210. [3] SHA T Y,YANG G J,CHENG Z Q.A Brief Account of theForecast Products Based on the Forecast Texts of Ensemble Prediction from ECMWF [J].Guangdong Meteorology,2015,37(1):4-9. [4] CUN Y L,DENKER J S,SOLLA S A.Optimal brain damage [C]//International Conference on Neural Information Proces-sing Systems.1989. [5] KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks[C]//Proceedings of NIPS 2012.2012. [6] ZHOU F Y,JIN L P,DONG J,et al.Review of convolutional neual network[J].Chinese Journal of Computers,2017,40(6):1229-1251. [7] SZELISKI R.Computer vision:algorithms and applications[M].New York:Springer,2010:83-132. [8] ZHENG Y Q,YANG X F,LI Z W.Detection of severe convective cloud over sea surface from geostationary meteorological satellite images based on deep learning[J].Journal of Remote Sensing(Chinese),2020,24(1):97-106. [9] ZOU G L,HOU Q,ZHENG Z S,et al.Classification of Typhoon Grade Based on Satellite Cloud Image and Deep Learning [J].Remote Sensing Information,2019,34(3):1-6. [10] SU H,WU L,JIANG J H,et al.Applying satellite observations of tropical cyclone internal structures to rapid intensication forecast with machine learning[J].Geophysical Research Letters,2020,47:e2020GL089102. [11] REICHSTEIN M,CAMPS-VALLS G,STEVENS B,et al.Deep learning and process understanding for data-driven Earth system science[J].Nature,2019,566:195-204. [12] WMO 2019:Typhoon Committee Operational Manual - Meteorological Component[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-23,WMO/TD-No.196. [13] WMO 2008:Guide to meteorological instruments and methods of observation[OL].http://www.seedmech.com/documents_folder/wmo_no_8.pdf. [14] WMO 2003a:Regional association IV (North and Central America and the Caribbean) hurricane operational plan[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-30,WMO/TD-No.494. [15] WMO 2003b:Typhoon committee operational manual meteorological component[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-23,WMO/TD-No.196. [16] WMO 2002b:Tropical cyclone operational plan for the Bay ofBengal and the Arabian Sea[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-21,WMO/TD-No.84. [17] WMO 2002c:Tropical cyclone operational plan for the South-West Indian Ocean[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-12,WMO/TD-No.577. [18] WMO 2002a:Tropical cyclone operational plan for the SouthPacific and South-East Indian Ocean[R].World Meteorological Organization,Tropical Cyclone Programme Report No.TCP-24,WMO/TDNo.292. [19] China Meteorological Administration.Typhoon business andservice regulations[M].Beijing:Meteorological Press,2012. [20] HWANG J,ORENSTEIN P,COHEN J,et al.Improving Subseasonal Forecasting in the Western U.S.with Machine Lear-ning[C]//The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'19).ACM,New York,2019:14. [21] IGLESIAS G,KALE D C,LIU Y.An examination of deeplearning for extreme climate pattern analysis.In The 5th International Workshop on Climate Informatics[C]//Boulder,CO,USA,2015. [22] PAOLETTI M E,HAUT J M,PLAZA J,et al.A new deep convolutional neural network for fast hyperspectral image classification[J].ISPRS Journal of Photogrammetry and Remote Sen-sing,2017,S0924271617303660. [23] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [24] KNAFF J A,LONGMORE S P,DEARIA R T,et al.Improved tropical-cyclone flight-level wind estimates using routine infrared satellite reconnaissance[J].J.Appl.Meteor.Climat.,2015,54(2):463-478. [25] MUELLER K J,DEMARIA M,KNAFF J,et al.Objective Estimation of Tropical Cyclone Wind Structure from Infrared Satellite Data [J].Weather & Forecasting,2006,21(6):990-1005. [26] ZEHR R M.Tropical cyclone research using large infrared data sets[C]//Preprints,24th Conf.on Hurricanes and Tropical Meteorology.2000:486-487. |
[1] | 陈志强, 韩萌, 李慕航, 武红鑫, 张喜龙. 数据流概念漂移处理方法研究综述 Survey of Concept Drift Handling Methods in Data Streams 计算机科学, 2022, 49(9): 14-32. https://doi.org/10.11896/jsjkx.210700112 |
[2] | 周旭, 钱胜胜, 李章明, 方全, 徐常胜. 基于对偶变分多模态注意力网络的不完备社会事件分类方法 Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification 计算机科学, 2022, 49(9): 132-138. https://doi.org/10.11896/jsjkx.220600022 |
[3] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
[4] | 胡安祥, 尹小康, 朱肖雅, 刘胜利. 基于数据流特征的比较类函数识别方法 Strcmp-like Function Identification Method Based on Data Flow Feature Matching 计算机科学, 2022, 49(9): 326-332. https://doi.org/10.11896/jsjkx.220200163 |
[5] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
[6] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[7] | 陈坤峰, 潘志松, 王家宝, 施蕾, 张锦. 基于双目叠加仿生的微换衣行人再识别 Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation 计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140 |
[8] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
[9] | 闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042 |
[10] | 高振卓, 王志海, 刘海洋. 嵌入典型时间序列特征的随机Shapelet森林算法 Random Shapelet Forest Algorithm Embedded with Canonical Time Series Features 计算机科学, 2022, 49(7): 40-49. https://doi.org/10.11896/jsjkx.210700226 |
[11] | 杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070 |
[12] | 张洪博, 董力嘉, 潘玉彪, 萧宗志, 张惠臻, 杜吉祥. 视频理解中的动作质量评估方法综述 Survey on Action Quality Assessment Methods in Video Understanding 计算机科学, 2022, 49(7): 79-88. https://doi.org/10.11896/jsjkx.210600028 |
[13] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
[14] | 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198 |
[15] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
|