Forecasting of typhoon wave based on hybrid machine learning models

被引:8
|
作者
Gong, Yijie [1 ]
Dong, Sheng [1 ]
Wang, Zhifeng [1 ]
机构
[1] Ocean Univ China, Coll Engn, Qingdao 266100, Peoples R China
基金
中国国家自然科学基金;
关键词
Typhoon wave; Real-time forecast; Hybrid multi -layer perceptron; Hybrid genetic expression programming; Machine learning; ARTIFICIAL NEURAL-NETWORK; PREDICTION; HEIGHT;
D O I
10.1016/j.oceaneng.2022.112934
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
The generation of typhoon waves is associated with both marine meteorological factors and continuous dynamic time series. This study develops a hybrid multi-layer perceptron (HMLP) neural network and a hybrid genetic expression programming (HGEP) model with a switch layer to forecast the typhoon waves. The switch layer transforms the input data as vectors with specified time delay under the precondition of the physical-based essence modeled. Metocean data from 55 typhoons passing through the Fujian and Taiwan sea areas are used as training data. Typhoon Talim was tested on ten test sites in the research area, and the forecast lead time was set to 3h, 6h, 12h, and 24h. The hybrid models can forecast the significant wave height well, with RAE no more than 0.83 and RRSE no more than 0.8. The actually occurred Typhoon Lekima and Typhoon Mitag were tested and observed, and showed an agreement between test data, forecast results, and observed data. The influence factors of forecast performance are discussed. The amount of training typhoons and the similarity of training typhoon tracks to target typhoon have influence on the forecast results. The forecast performance is related to the impact intensity of the typhoon on the test sites.
引用
收藏
页数:21
相关论文
共 50 条
  • [21] Machine learning models for renewable energy forecasting
    Tharani, Kusum
    Kumar, Neeraj
    Srivastava, Vishal
    Mishra, Sakshi
    Pratyush Jayachandran, M.
    JOURNAL OF STATISTICS & MANAGEMENT SYSTEMS, 2020, 23 (01): : 171 - 180
  • [22] Machine Learning Models for Spring Discharge Forecasting
    Granata, Francesco
    Saroli, Michele
    de Marinis, Giovanni
    Gargano, Rudy
    GEOFLUIDS, 2018,
  • [23] Rainfall forecasting by technological machine learning models
    Hong, Wei-Chiang
    APPLIED MATHEMATICS AND COMPUTATION, 2008, 200 (01) : 41 - 57
  • [24] Probabilistic forecasting of flood processes based on hybrid deep learning models
    Cui Z.
    Guo S.
    Wang J.
    Zhang J.
    Zhou Y.
    Shuili Xuebao/Journal of Hydraulic Engineering, 2023, 54 (08): : 889 - 909
  • [25] A comparative study of traditional machine learning and hybrid fuzzy inference system machine learning models for air quality index forecasting
    Ordenshiya, K. M.
    Revathi, Gk
    INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS, 2025,
  • [26] A hybrid approach based machine learning models in electricity markets
    Gomez, William
    Wang, Fu-Kwun
    Lo, Shih-Che
    ENERGY, 2024, 289
  • [27] A Hybrid Time Series Forecasting Method Based on Supervised Machine Learning Program
    Khuntia, Ganesh Prasad
    Dash, Ritesh
    Swain, Sarat Chandra
    Bawaney, Prashant
    ADVANCES IN DATA SCIENCE AND MANAGEMENT, 2020, 37 : 81 - 90
  • [28] Hybrid model for microgrid short term load forecasting based on machine learning
    Khayat, Ahmed
    Kissaoui, Mohammed
    Bahatti, Lhoussaine
    Raihani, Abdelhadi
    Errakkas, Khalid
    Atifi, Youness
    IFAC PAPERSONLINE, 2024, 58 (13): : 527 - 532
  • [29] Hybrid river stage forecasting based on machine learning with empirical mode decomposition
    Heddam, Salim
    Vishwakarma, Dinesh Kumar
    Abed, Salwan Ali
    Sharma, Pankaj
    Al-Ansari, Nadhir
    Alataway, Abed
    Dewidar, Ahmed Z.
    Mattar, Mohamed A.
    APPLIED WATER SCIENCE, 2024, 14 (03)
  • [30] Portability of Hybrid machine learning based model for anomaly forecasting in mobile networks
    Kassan, Sara
    Hadj-Kacem, Imed
    Ben Jemaa, Sana
    Allio, Sylvain
    2023 IEEE 98TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2023-FALL, 2023,