人工智能新技术在国家气象中心台风业务中的应用探索

周冠博; 钱奇峰; 吕心艳; 刘春霞; 徐雅静

doi:10.16032/j.issn.1004-4965.2022.043

人工智能新技术在国家气象中心台风业务中的应用探索

doi: 10.16032/j.issn.1004-4965.2022.043

周冠博^{1, 2},
钱奇峰^1, ,,
吕心艳¹,
刘春霞³,
徐雅静⁴

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
3.
中国气象局广州热带海洋气象研究所，广东广州 510641
4.
北京邮电大学，北京 100876

基金项目:

广东省重点领域研发计划项目 2019B111101002

国家重点研发计划项目 2017YFC1501604

灾害天气国家重点实验室开放课题 2022LASW-B09

气象预报业务关键技术发展专项 YBGJXM(2020)3A-03

详细信息

通讯作者:
钱奇峰，男，江苏省人，高级工程师，主要从事台风预报和研究。E-mail：qianqf@cma.gov.cn

中图分类号: P444
计量
- 文章访问数: 75
- HTML全文浏览量: 8
- PDF下载量: 25
- 被引次数: 0
出版历程
- 收稿日期: 2022-01-14
- 修回日期: 2022-05-08
- 网络出版日期: 2022-10-25
- 刊出日期: 2022-08-20

APPLICATION OF ARTIFICIAL INTELLIGENCE IN TYPHOON MONITORING AND FORECASTING

1.
National Meteorological Center, Beijing 100081, China
2.
State key Laboratory of Severe Weather, Chinese Academy of Meteorological Sciences, Beijing 100081, China
3.
Guangzhou Institute of Tropical and Marine Meteorology, China Meteorological Administration, Guangzhou 510641, China
4.
Beijing University of Posts and Telecommunications, Beijing 100876, China

摘要

摘要: 基于2005—2020年的中国气象局台风最佳路径数据集以及葵花（Himawari-8）和风云（FY-4）卫星云图数据，结合人工智能新技术，将深度学习模型应用于台风涡旋识别、台风定位定强、台风强度突变预测等方面，具体内容主要包括基于深度图像目标检测的台风涡旋识别模型、基于图像分类和检索的台风智能定强模型以及融合时空序列特征的台风快速增强判别模型，构建了一套台风智能监测和预报系统。通过对2020年全年样本进行了测试，结果显示：该系统对强热带风暴级及以上强度的台风涡旋正确识别率达90%以上，台风强度估测的MAE和RMSE分别为3.8 m/s和5.05 m/s，对全年独立样本强度快速加强预测的综合准确率达到65.3%，该系统实现了业务上利用高时空分辨率卫星图像实时对热带气旋进行自动识别、定位定强和智能追踪的功能，为进一步提高我国台风监测和预报预警的能力提供了有利支撑。
- 深度学习 /
- 台风涡旋识别 /
- 智能定强 /
- 快速增强 /
- 卫星云图
Abstract: Based on the typhoon optimal path data set from China Meteorological Administration during 2005 and 2020, and the Himawari-8 and FY4 satellites cloud image data, combined with the new technology of artificial intelligence, this paper applies deep learning models to typhoon vortex identification, typhoon location and intensity determination, typhoon intensity change detection, etc. To be specific, the new technology has been applied to develop a typhoon vortex identification model based on depth image target detection, a typhoon intensity intelligent determination model based on image classification and retrieval, and a typhoon rapid enhancement discrimination model considering the characteristics of time and space series. Tests with all the samples of vortices occurred in 2020 show that the correct identification rate of typhoon vortex with intensity reaching strong tropical storm or stronger is over 90%, the mean absolute error and root mean squared error of typhoon intensity estimation are 3.8 m/s and 5.05 m/s, respectively, and the comprehensive accuracy rate of annual independent sample intensity rapid enhancement estimation is 65.3%. The system realizes the automatic identification, positioning, intensity determination, and real-time intelligent tracking of tropical cyclones by using satellite images with high spatial and temporal resolution.
- deep learning /
- typhoon vortex identification /
- intelligent intensity determination /
- rapid intensification /
- satellite images

HTML全文

图 1 基于深度图像目标检测的智能台风涡旋识别的技术模型

下载: 全尺寸图片幻灯片

图 2 台风涡旋识别率检验结果

下载: 全尺寸图片幻灯片

图 3 基于图像分类和检索的台风定强的技术模型

下载: 全尺寸图片幻灯片

图 4 台风智能定强的ResNet模型对2020年全年样本强度估测的MAE（a）和RMSE（b）

下载: 全尺寸图片幻灯片

图 5 台风强度快速增强趋势判别的技术模型

下载: 全尺寸图片幻灯片

图 6 台风“天鹅”模型预测的突变概率（紫色星号）与实况突变概率（绿色圆点）比较

下载: 全尺寸图片幻灯片

图 7 基于人工智能的台风监测和预报系统

a. 2020年11月1日09 UTC的FY-4A卫星的圆盘图；b. 范围70~160 °E，20 °S~70 °N投影区域；c. 2019号台风“天鹅”的云图；d. 2020号台风“艾莎尼”的云图。

下载: 全尺寸图片幻灯片

图 8 a~d. 2019号台风“天鹅”的连续4个时刻的卫星遥感云图，截至（2020年10月29日18 UTC）提取遥感云图时空特征和已知的强度信息序列；e~h. 2020号台风“艾莎尼”的连续4个时刻的卫星遥感云图，截至（2020年11月4日12 UTC）提取遥感云图时空特征和已知的强度信息序列

下载: 全尺寸图片幻灯片

表 1 模型对2020年云图台风样本的强度估测分析

等级	样本数/个	模型估计（MAE）/(m/s)	模型估计（RSME）/(m/s)
热带低压	25	3.12	4.62
热带风暴	413	2.66	3.89
强热带风暴	200	5.04	6.08
台风	128	6.16	7.81
强台风	82	4.45	5.50
超强台风	20	3.85	6.67
合计（平均）	868	3.93	5.40

下载: 导出CSV

参考文献(26)

[1]	RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252. doi: 10.1007/s11263-015-0816-y
[2]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[J]. IEEE, 2016: 770-778.
[3]	XIE S, TU Z. Holistically-Nested Edge Detection[J]. International Journal of Computer Vision, 2015, 125(1-3): 3-18.
[4]	KARPATNE A, EBERT-UPHOFF I, RAVELA S, et al. Machine learning for the geosciences: Challenges and opportunities[J]. IEEE Transactions on Knowledge & Data Engineering, 2018, 31(8): 1 544-1 554.
[5]	MCGOVERN A, ELMORE K L, GAGNE D, et al. Using artificial intelligence to improve real-time decision-making for high-impact weather[J]. Bulletin of the American Meteorological Society, 2017, 98(10): 2 073-2 090. doi: 10.1175/BAMS-D-16-0123.1
[6]	MARKUS R, GUSTAU G, BJORN S, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204. doi: 10.1038/s41586-019-0912-1
[7]	SHI X, CHEN Z, WANG H, et al. Convolutional LSTM Network: A machine learning approach for precipitation nowcasting[J]. MIT Press, 2015: 802-810.
[8]	CHRISTODOULOU C I, MICHAELIDES S C, PATTICHIS C S. Multifeature texture analysis for the classification of clouds in satellite imagery[J]. Geoscience & Remote Sensing IEEE Transactions on, 2003, 41(11): 2 662-2 668.
[9]	RAMIREZ S, LIZARAZO I. Detecting and tracking mesoscale precipitating objects using machine learning algorithms[J]. International Journal of Remote Sensing, 2017, 38(18): 5 045-5 068. doi: 10.1080/01431161.2017.1323280
[10]	SHI J, WANG P, WANG D, et al. Radar-based hail-producing storm detection using positive unlabeled classification[J]. Technical Gazette, 2020, 27(3): 941-950.
[11]	LIAN J, DONG P, ZHANG Y, et al. A novel data-driven tropical cyclone track prediction model based on CNN and GRU with multidimensional feature selection[J]. IEEE Access, 2020, 8: 97 114-97 128. doi: 10.1109/ACCESS.2020.2992083
[12]	WIMMERS A, VELDEN C, COSSUTH J H. Using deep learning to estimate tropical cyclone intensity from satellite passive microwave imagery[J]. Mont Wea Rev, 2019, 147(6): 2 261-2 282. doi: 10.1175/MWR-D-18-0391.1
[13]	BAIK J J, PAEK J S. A neural network model for predicting typhoon intensity[J]. Journal of the Meteorological Society of Japan, 2000, 78 (6): 857-869.
[14]	CHAUDHURI S, DUTTA D, GOSWAMI S, et al. Intensity forecast of tropical cyclones over North Indian Ocean using multilayer perceptron model: skill and performance verification[J]. Natural Hazards, 2013, 65(1): 97-113. doi: 10.1007/s11069-012-0346-7
[15]	PAN B, XU X, SHI Z W. Tropical cyclone intensity prediction based on recurrent neural networks[J]. Electronics Letters, 2019, 55(7): 413-415. doi: 10.1049/el.2018.8178
[16]	CHEN B, CHEN B F, LIN H T, et al. Estimating tropical cyclone intensity by satellite imagery utilizing convolutional neural networks[J]. Weather Forecast, 2019, 34: 447-465. doi: 10.1175/WAF-D-18-0136.1
[17]	JIN Q, FAN X, LIU J, et al. Estimating Tropical Cyclone Intensity in the South China Sea Using the XGBoost Model and FengYun Satellite Images[J]. Atmosphere, 2020, 11(4): 423. doi: 10.3390/atmos11040423
[18]	马雷鸣. 天气预报中的人工智能技术进展[J]. 地球科学进展, 2020, 35(6): 551-560. https://www.cnki.com.cn/Article/CJFDTOTAL-DXJZ202006001.htm
[19]	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): 692-702. doi: 10.1109/TIP.2017.2766358
[20]	TIAN W, WEI H, XU X, 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 (SmartData). IEEE, 2019.
[21]	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(2): 1-6. https://www.cnki.com.cn/Article/CJFDTOTAL-GXQX202002002.htm
[22]	MATSUOKA D, NAKANO M, SUGIYAMA D, et al. Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model[J]. Progress in Earth and Planetary Science, 2018, 5(1): 1-16. doi: 10.1186/s40645-017-0157-2
[23]	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(5): 36-43. https://www.cnki.com.cn/Article/CJFDTOTAL-QXKZ201205009.htm
[24]	鲁小琴, 雷小途, 余晖, 等. 基于卫星资料进行热带气旋强度客观估算[J]. 应用气象学报, 2014, 25(1): 52-58. https://www.cnki.com.cn/Article/CJFDTOTAL-YYQX201401006.htm
[25]	COMBINIDO J S, MENDOZA J R, ABOROT J. A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images[C]//2018 24th International Conference on Pattern Recognition (ICPR). 2018.
[26]	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. doi: 10.3969/j.issn.1000-3177.2019.03.001