APPLICATION OF ARTIFICIAL INTELLIGENCE IN TYPHOON MONITORING AND FORECASTING
-
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。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.
-
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 -
[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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. [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. -