Using a 3D convolutional neural network and gated recurrent unit for tropical cyclone track forecasting

被引:9
|
作者
Wang, Pingping [1 ,3 ]
Wang, Ping [1 ,3 ]
Wang, Cong [1 ,3 ]
Xue, Bing [2 ,3 ]
Wang, Di [1 ,3 ]
机构
[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin, Peoples R China
[2] CMA Publ Meteorol Serv Ctr, Beijing, Peoples R China
[3] CMA Publ Meteorol Serv Ctr, Joint Lab Intelligent Identificat & Nowcasting Se, Beijing, Peoples R China
关键词
Tropical cyclone; 3DCNN; GRU; Track forecasting; Machine learning; HURRICANE; INTENSITY; MODEL; ENSEMBLE; SYSTEMS; SHEAR;
D O I
10.1016/j.atmosres.2022.106053
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
The tropical cyclone (TC) track forecast is an essential task in meteorological operations. An accurate forecast should be based on a comprehensive understanding and description of TCs. A TC has a complex threedimensional structure, and the surrounding atmosphere is the driving force for its development. Traditional forecasting methods performed relatively well for the TCs with stable moving speed and direction. However, the forecast accuracy still leaves some space to improve. In recent years, machine learning methods that can extract features from a large amount of historical data have been used in meteorological services and have shown excellent performance. To better forecast 6, 12, 18, and 24 h TC tracks in the Western North Pacific, a hybrid optimization model, combining the 3D convolutional neural network (3DCNN), gated recurrent unit (GRU), and smoothing algorithm is designed, which is called smoothed 3D-GRU. The 3DCNN is used to explore the potential relationship between environmental variables and TC movements at different pressure levels. The GRU is used to convert the TC track forecasting problem into a spatio-temporal sequence problem. The smoothing algorithm is used as a post-processing method to suppress unreasonable jumps of the model output. The mean spherical distances (MSDs) of the proposed smoothed 3D-GRU model at four prediction times are 27.89, 52.37, 79.16, and 112.05 km, which are lower than the comparative machine learning-based forecasting algorithms. Compared with the numerical prediction methods, the MSDs of the smoothed 3D-GRU model are lower in most situations. In general, the smoothed 3D-GRU model can provide reliable guidance for the TC trajectory prediction.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Automatic Detection of Power Quality Disturbance Using Convolutional Neural Network Structure with Gated Recurrent Unit
    Yigit, Enes
    Ozkaya, Umut
    Ozturk, Saban
    Singh, Dilbag
    Gritli, Hassene
    MOBILE INFORMATION SYSTEMS, 2021, 2021
  • [22] Real Time Human Activity Recognition Using Convolutional Neural Network and Deep Gated Recurrent Unit
    Fajar, Rasyid
    Suciati, Nanik
    Navastara, Dini Adni
    2020 INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND INFORMATICS (ICELTICS 2020), 2020, : 58 - 63
  • [23] Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network
    Shi, Hanhong
    Wang, Lei
    Scherer, Rafal
    Wozniak, Marcin
    Zhang, Pengchao
    Wei, Wei
    IEEE ACCESS, 2021, 9 : 66965 - 66981
  • [24] An Ensemble 3D Convolutional Neural Network for Spatiotemporal Soil Temperature Forecasting
    Yu, Fanhua
    Hao, Huibowen
    Li, Qingliang
    SUSTAINABILITY, 2021, 13 (16)
  • [25] Track Condition Evaluation for Multi-vehicle Performance Prediction Model Based on Convolutional Neural Network and Gated Recurrent Unit
    Yang F.
    Hao X.
    Yang J.
    Sun X.
    Gao Y.
    Zhang Y.
    Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2023, 58 (02): : 322 - 331
  • [26] Convolutional Neural Network-Gated Recurrent Unit Neural Network with Feature Fusion for Environmental Sound Classification
    Jinfang Yu Zhang
    Youming Zeng
    Da Li
    Automatic Control and Computer Sciences, 2021, 55 : 311 - 318
  • [27] Convolutional Neural Network-Gated Recurrent Unit Neural Network with Feature Fusion for Environmental Sound Classification
    Zhang, Yu
    Zeng, Jinfang
    Li, Youming
    Chen, Da
    AUTOMATIC CONTROL AND COMPUTER SCIENCES, 2021, 55 (04) : 311 - 318
  • [28] Recognition of meal information using recurrent neural network and gated recurrent unit
    Zhang, Liyang
    Suzuki, Hiroyuki
    Koyama, Akio
    INTERNET OF THINGS, 2021, 13
  • [29] Toxic Comment Classification Based on Bidirectional Gated Recurrent Unit and Convolutional Neural Network
    Wang, Zhongguo
    Zhang, Bao
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2022, 21 (03)
  • [30] Dysarthria Speech Detection Using Convolutional Neural Networks with Gated Recurrent Unit
    Shih, Dong-Her
    Liao, Ching-Hsien
    Wu, Ting-Wei
    Xu, Xiao-Yin
    Shih, Ming-Hung
    HEALTHCARE, 2022, 10 (10)