[1]周冠博,钱奇峰,吕心艳,等.人工智能在台风监测和预报中的探索与展望[J].气象研究与应用,2022,43(02):1-8.[doi:10.19849/j.cnki.CN45-1356/P.2022.2.01]
　Zhou Guanbo,Qian Qifeng,Lv Xinyan,et al.Application and expectation of artificial intelligence in typhoon monitoring and forecasting[J].Journal of Meteorological Research and Application,2022,43(02):1-8.[doi:10.19849/j.cnki.CN45-1356/P.2022.2.01]
点击复制

人工智能在台风监测和预报中的探索与展望()
分享到：

气象研究与应用[ISSN:1673-8411/CN:45-1356/P]

卷:
第43卷
期数:
2022年02期
页码:
1-8
栏目:
综述
出版日期:
2022-06-15

文章信息/Info

Title:
Application and expectation of artificial intelligence in typhoon monitoring and forecasting
作者:
周冠博1; 2;  钱奇峰1;  吕心艳1;  聂高臻1
1. 国家气象中心, 北京 100081;
2. 中国气象科学研究院灾害天气国家重点实验室, 北京 100081
Author(s):
Zhou Guanbo1; 2;  Qian Qifeng1;  Lv Xinyan1;  Nie Gaozhen1
1. National Meteorological Center, Beijing 100081, China;
2. National Key Laboratory for Disaster Weather of Chinese Academy of Meteorological Sciences, Beijing 100081, China
关键词:
人工智能; 台风监测; 路径预报; 强度预报; 集合预报
Keywords:
artificial intelligence; typhoon monitoring; path forecasting; intensity forecasting; ensemble forecasting
分类号:
P457.8
DOI:
10.19849/j.cnki.CN45-1356/P.2022.2.01
摘要:
随着人工智能（AI）新技术的日益兴起，在气象大数据背景下，对具有强大的数据学习能力和复杂结构特征刻画能力的深度学习进行研究有着十分广阔的应用场景。针对当前人工智能新技术在台风监测和预报中的应用与发展进行了简要的回顾，同时介绍了国家气象中心目前结合人工智能新技术在台风的客观定位定强、路径预报以及强度突变预测等方面所做的尝试，最后提出了人工智能新方法在台风监测和预报业务应用中存在的问题以及未来的工作展望。
Abstract:
In recent years, artificial intelligence technology has occupied an important position in the field of artificial intelligence, and has become a hot spot in contemporary scientific research, especially in image recognition, which shows great potential advantages, has a great enlightenment on the development of meteorological field, and also provides new ideas and directions for typhoon monitoring and forecasting in meteorological field. In this paper, the application and development of artificial intelligence technology in typhoon monitoring and forecasting are reviewed. Finally, the existing problems and future work prospects of artificial intelligence methods in typhoon monitoring and forecasting are given.

参考文献/References:

[1] 端义宏,陈联寿,梁建茵,等.台风登陆前后异常变化的研究进展[J]. 气象学报, 2014,72(5),969-986.
[2] 端义宏,陈联寿,许映龙,等.我国台风监测预报预警体系的现状及建议[J]. 中国工程科学, 2012,14(9):4-9.
[3] 周冠博,柳龙生,董林,等. 2020年西北太平洋台风活动特征和预报难点分析[J]. 气象, 2022,48(4):504-515.
[4] 吕心艳,许映龙,董林,等. 2018年西北太平洋台风活动特征和预报难点分析[J]. 气象,2021,47(3):359-372.
[5] 钱传海,端义宏,麻素红,等. 我国台风业务现状及其关键技术[J].气象科技进展, 2012,2(5):36-43.
[6] Emanuel K,Zhang F Q.On the Predictability and Error Sources of Tropical Cyclone Intensity Forecasts[J]. Journal of the Atmospheric Sciences, 2016,73(9):3739-3747.
[7] 吴影,陈佩燕,雷小途. 登陆热带气旋路径和强度预报的效益评估初步研究[J]. 热带气象学报,2017,33(5):675-682.
[8] Bhatia K T,Nolan D S,Schumacher A B,et al. Improving Tropical Cyclone Intensity Forecasts with PRIME[J]. Weather and Forecasting,2017,32(4):1353-1377.
[9] Cecil D J, Zipser E J. Relationships between Tropical Cyclone Intensity and Satellite-Based Indicators of Inner Core Convection:85-GHz Ice-Scattering Signature and Lightning[J].American Meteorological Society,1999:103-123.
[10] Velden C S,Harper B,Wells F,et al. The Dvorak Tropical Cyclone Intensity Estimation Technique:A Satellite-Based Method that has Endured for over 30 Years[J]. Bulletin of the American Meteorological Society,2006,87(9):1195-1210.
[11] Olander T L,Velden C S. Tropical Cyclone Convection and Intensity Analysis Using Differenced Infrared and Water Vapor Imagery[J].Weather and Forecasting,2009,24(6):1558-1572.
[12] Ritchie L,Valliere K G,Pi?ros M F, et al. Tropical Cyclone Intensity Estimation in the North Atlantic Basin Using an Improved Deviation Angle Variance Technique[J]. Weather and Forecasting, 2012,27(5),1264-1277.
[13] Dvorak V F.Tropical Cyclone Intensity Analysis and Forecasting from Satellite Imagery[J]. American Meteorological Society, 1975:420-430.
[14] Dvorak V F. Tropical Cyclone Intensity Analysis Using Satellite Data[J]. National Oceanic and Atmospheric Administration, National Earth Satellite Service, 1984.
[15] 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]. American Meteorological Society,1998:172-186.
[16] Olander T L,Velden C S.The Advanced Dvorak Technique:Continued Development of an Objective Scheme to Estimate Tropical Cyclone Intensity Using Geostationary Infrared Satellite Imagery[J]. Weather and Forecasting, 2007,22(2):287-298.
[17] 许映龙,张玲,向纯怡.台风定强技术及业务应用-以Dvorak技术为例[J]. 气象科技进展,2015,5(4):22-34.
[18] Krizhevsky A, Hinton G. Learning Multiple Layers of Features from Tiny Images[J].Handbook of Systemic Autoimmune Diseases,2009,1(4):1-10.
[19] Krizhevsky A,Sutskever I,Hinton G.ImageNet Classification with Deep Convolutional Neural Networks[J].Advances in Neural Information Processing Systems,2012:1097-1105.
[20] He K M, Zhang X Y,Ren S Q, et al. Deep Residual Learning for Image Recognition[C]//. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
[21] 崔林丽,郭巍,葛伟强,等. FY-4A卫星云顶参数精度检验及台风应用研究[J].高原气象,2020,39(1):196-203.
[22] Zhang C J,Wang X J, Ma L M, et al. Tropical Cyclone Intensity Classification and Estimation Using Infrared Satellite Images with Deep Learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021.
[23] Zhuo J, Tan Z M. Physics-Augmented Deep Learning to Improve Tropical Cyclone Intensity and Size Estimation from Satellite Imagery[J].Monthly Weather Review, 2021, 149(7):2097-2113.
[24] 严军, 刘健文.基于神经网络奇异谱分析的ENSO指数预测[J]. 大气科学,2005, 29(4):620-626.
[25] 陈刚毅, 丁旭羲, 赵丽妍.用模糊神经网络自动识别云的技术研究[J]. 大气科学,2005, 29(5):837-844.
[26] 金龙, 秦伟良, 姚华栋.多步预测的小波神经网络预报模型[J]. 大气科学,2000, 24(1):79-86.
[27] 刘妹琴.离散时滞标准神经网络模型及其应用[J]. 中国科学E辑:信息科学, 2005,35(10):1031-1048.
[28] 曹祥村,邵利民.一种利用BP网络预报台风路径的新方法[J]. 海洋预报,2007(3):75-82.
[29] 洪梅, 张韧, 吴国雄, 等.用遗传算法重构副热带高压特征指数的非线性动力模型[J]. 大气科学,2007,31(2):346-352.
[30] 胡娅敏, 丁一汇, 沈桐立.基于遗传算法的四维变分资料同化技术的研究[J]. 大气科学,2006,30(2):248-256.
[31] Zheng D, Liang R, Zhou Y, et al. A Chaos Genetic Algorithm for Optimizing an Artificial Neural Network of Prediction Silicon Content in Hot Metal[J].International Journal of Minerals Metallurgy and Materials, 2003.
[32] 郭章林, 刘明广, 解德才.震灾经济损失评估的遗传神经网络模型[J]. 自然灾害学报, 2004,13(6):92-96.
[33] Huang X Y,Jin L,Shi X M. A Nonlinear Artificial Intelligence Ensemble Prediction Model Based on EOF for Typhoon Track[C]//.Fourth International Joint Conference on Computational Sciences and Optimization,2011.
[34] Jin L, Yao C, Huang X Y. A Nonlinear Artificial Intelligence Ensemble Prediction Model for Typhoon Intensity[J]. Monthly Weather Review,2008, 136:4541-4554.
[35] 黄小燕,金龙.基于主成分分析的人工智能台风路径预报模型[J]. 大气科学,2013,37(5):1154-1164.
[36] 王瀚.基于深度学习的台风路径预测多模型算法研究[D].成都:电子科技大学, 2020.
[37] 邵利民,傅刚,曹祥村,等. BP神经网络在台风路径预报中的应用[J]. 自然灾害学报,2009,18(6):104-111.
[38] 吕庆平,罗坚,朱坤,等.基于SVM的气候持续法在热带气旋路径预报中的应用试验[J]. 海洋预报,2009,26(1):76-83.
[39] 朱雷.基于神经网络委员会机器的南中国海台风路径预报模型研究[D].上海:华东师范大学,2017.
[40] 周笑天, 张丰, 杜震洪, 等.基于神经网络集合预报的台风路径预报优化[J].浙江大学学报(理学版),2020,47(2):196-204,217.
[41] Rüttgers M, Lee S,Jeon S, et al. Prediction of a Typhoon Track Using a Generative Adversarial Network and Satellite Images[J]. Scientific Reports, 2019,9(1).
[42] Pradhan R, Aygun R S, Maskey M, et al. Tropical Cyclone Intensity Estimation Using a Deep Convolutional Neural Network[J]. IEEE Transactions on Image Processing,2018,27(2).
[43] Zahera H M, Sherif M A, Ngonga A C N. Jointly Learning from Social Media and Environmental Data for Typhoon Intensity Prediction[C]//. Proceeding of the 10th International Conference on Knowledge Capture,2019:231-234.
[44] Chen B,Chen B F,Lin H T.Rotation-Blended CNNs on a New Open Dataset for Tropical Cyclone Image-to-Intensity Regression[C]//. Zn Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining,2018:90-99.
[45] Wei T,Wei H W,Xu X L,et al.Tropical Cyclone Maximum Wind Estimation from Infrared Satellite Data with Integrated Convolutional Neural Networks[C]//. 2019 International Conference on Internet of Things(iThings) and IEEE Green Computing and Communications(GreenCom) and IEEE Cyber,Physical and Social Computing(CPSCom) and IEEE Smart Data(Smart-Data),2019:575-580.
[46] 张淼,覃丹宇,邱红.基于FY-3C/MWTS-Ⅱ数据估计西北太平洋热带气旋强度[J]. 气象,2017,43(5):573-580.
[47] Combinido J S, Mendoza J R,Aborot J.A Convolutional Neural Network Approach for Estimating Tropical Cyclone Intensity Using Satellite-based Infrared Images[C]//. 201824th International Conference on Pattern Recognition (ICPR),2018.
[48] 邹国良,侯倩,郑宗生,等.面向卫星云图及深度学习的台风等级分类[J]. 遥感信息,2019,34(3):1-6.
[49] Chen B F,Davis C A,Kuo Y H.Effects of Low-Level Flow Orientation and Vertical Shear on the Structure and Intensity of Tropical Cyclones[J]. Monthly Weather Review, 2018,146:2447-2467.
[50] Chen B F, Chen B, Lin H T, et al. Estimating Tropical Cyclone Intensity by Satellite Imagery Utilizing Convolutional Neural Networks[J].Weather and Forecasting,2019, 34(2):447-465.
[51] Xu Y J,Yang H T,Cheng M F,et al.Cyclone Intensity Estimate with Context-Aware Cyclegan[C]//. ICIP 2019,2019:3417-3421.
[52] Chen B, Chen B F, Chen Y N. Real-Time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data[J].2020.

相似文献/References:

[1]金龙,黄颖,姚才,等.人工智能技术的热带气旋预报综述（之一）——BP神经网络和集成方法的热带气旋预报研究和业务应用[J].气象研究与应用,2020,41(02):1.[doi:10.19849/j.cnki.CN45-1356/P.2020.2.01]
　Jin Long,Huang Ying,Yao Cai,et al.A review of tropical cyclone forecast based on artificial intelligence (part 1)——BP neural network and ensemble method for tropical cyclone forecast research and operational application[J].Journal of Meteorological Research and Application,2020,41(02):1.[doi:10.19849/j.cnki.CN45-1356/P.2020.2.01]
[2]李宗飞,陈凯华,赵玉娟.卷积神经网络和传统算法的雷达面雨量计算效果对比研究[J].气象研究与应用,2021,42(04):89.[doi:10.19849/j.cnki.CN45-1356/P.2021.4.16]
　Li zongfei,Chen Kaihua,Zhao Yujuan.A comparative study of convolution neural network and traditional algorithm in radar area rainfall calculation[J].Journal of Meteorological Research and Application,2021,42(02):89.[doi:10.19849/j.cnki.CN45-1356/P.2021.4.16]
[3]陈剑飞,李勇,刘俊江,等.耦合陆面水文模型和机器学习方法的水库径流量预报及应用[J].气象研究与应用,2022,43(01):1.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.01]
　Chen Jianfei,Li Yong,Liu Junjiang,et al.Yantan Reservoir runoff forecast and application coupled with land surface hydrological model and machine learning method[J].Journal of Meteorological Research and Application,2022,43(02):1.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.01]

备注/Memo

备注/Memo:
收稿日期:2022-04-10。
基金项目:国家重点研发计划项目（2017YFC1501604、2018YFC1506406）、灾害天气国家重点实验室开放课题、国家自然科学基金重点项目（41930972）、国家自然科学面上项目（41875056、42175016、42075013）和国家自然科学青年基金项目（41405049）
作者简介:周冠博,高级工程师,主要从事台风预报和研究。E-mail:zhougb@cma.gov.cn
通讯作者:钱奇峰,高级工程师,主要从事台风预报和研究。E-mail:qianqf@cma.gov.cn
更新日期/Last Update: 1900-01-01