(YIN Chengtuan, SUN Zhongbin, ZHANG Weisheng, et al. Study on the adjustment of maximum sustained wind speed based on the LightGBM Model[J]. Hydro-Science and Engineering(in Chinese)). DOI: 10.12170/20240718005
Citation: (YIN Chengtuan, SUN Zhongbin, ZHANG Weisheng, et al. Study on the adjustment of maximum sustained wind speed based on the LightGBM Model[J]. Hydro-Science and Engineering(in Chinese)). DOI: 10.12170/20240718005

Study on the adjustment of maximum sustained wind speed based on the LightGBM Model

More Information
  • Received Date: July 17, 2024
  • Available Online: March 25, 2025
  • The tropical cyclone (TC) maximum sustained wind speed is an important indicator for assessing the impact of typhoon disasters. Due to limitations in observational technology and differences in data compilation methods, there is a noticeable overestimation in the maximum sustained wind speed data of TC records before the 1970s. This study employed an improved empirical formula method and the LightGBM machine learning model to correct the maximum sustained wind speeds. The results showed that the empirical formula method generally performs well in correcting wind speeds, but the correction error increases rapidly when wind speeds are less than 20 m/s or greater than 52 m/s. The wind speed correction results using the LightGBM model demonstrate higher accuracy and stability, especially in high/low wind speed scenarios. The combined method outperformed either the formula method or the LightGBM model alone, reducing root mean square errors by 24.2% and 7.1%, respectively. The combined method proposed in this study can significantly enhance the precision of early TC maximum sustained wind speed data, providing reliable support for disaster assessment, storm surge forecasting, and coastal disaster mitigation policies.

  • [1]
    LU X Q, YU H, YING M, et al. Western North Pacific tropical cyclone database created by the China meteorological administration[J]. Advances in Atmospheric Sciences, 2021, 38(4): 690-699. doi: 10.1007/s00376-020-0211-7
    [2]
    于玉斌, 姚秀萍. 西北太平洋热带气旋强度变化的统计特征[J]. 热带气象学报,2006,22(6):521-526. (YU Yubin, YAO Xiuping. A statistical analysis on intensity change of tropical cyclone over the western North Pacific[J]. Journal of Tropical Meteorology, 2006, 22(6): 521-526. (in Chinese) doi: 10.3969/j.issn.1004-4965.2006.06.001

    YU Yubin, YAO Xiuping. A statistical analysis on intensity change of tropical cyclone over the western North Pacific[J]. Journal of Tropical Meteorology, 2006, 22(6): 521-526. (in Chinese) doi: 10.3969/j.issn.1004-4965.2006.06.001
    [3]
    陈锡璋. 西北太平洋热带气旋强度的若干气候特征[J]. 海洋通报,1997,16(4):16-25. (CHEN Xizhang. Some climatological characteristics of tropical cyclone intensity over the Northwestern Pacific[J]. Marine Science Bulletin, 1997, 16(4): 16-25. (in Chinese)

    CHEN Xizhang. Some climatological characteristics of tropical cyclone intensity over the Northwestern Pacific[J]. Marine Science Bulletin, 1997, 16(4): 16-25. (in Chinese)
    [4]
    殷成团, 张然, 熊梦婕, 等. 登陆我国热带气旋中心最低气压和最大风速关系研究[J]. 气象科学,2019,39(6):834-838. (YIN Chengtuan, ZHANG Ran, XIONG Mengjie, et al. A study on the relationship between minimum air pressure and maximum wind speed of landing tropical cyclone center in China[J]. Journal of the Meteorological Sciences, 2019, 39(6): 834-838. (in Chinese) doi: 10.3969/2018jms.0098

    YIN Chengtuan, ZHANG Ran, XIONG Mengjie, et al. A study on the relationship between minimum air pressure and maximum wind speed of landing tropical cyclone center in China[J]. Journal of the Meteorological Sciences, 2019, 39(6): 834-838. (in Chinese) doi: 10.3969/2018jms.0098
    [5]
    潘增弟, 梁晓东, 赵伟, 等. 海洋水文气象环境工程区划数值模拟研究[J]. 中国海洋平台,1997,12(6):264-268. (PAN Zengdi, LIANG Xiaodong, ZHAO Wei, et al. The numerical simulation research on the ocean hydrological environment engineering division[J]. China Offshore Platform, 1997, 12(6): 264-268. (in Chinese)

    PAN Zengdi, LIANG Xiaodong, ZHAO Wei, et al. The numerical simulation research on the ocean hydrological environment engineering division[J]. China Offshore Platform, 1997, 12(6): 264-268. (in Chinese)
    [6]
    周国良, 张建云, 刘九夫, 等. 西北太平洋热带气旋风压关系的变异分析[J]. 水科学进展,2011,22(6):750-755. (ZHOU Guoliang, ZHANG Jianyun, LIU Jiufu, et al. Variational analysis of the relationship between wind and pressure of tropical cyclones in Northwest Pacific[J]. Advances in Water Science, 2011, 22(6): 750-755. (in Chinese)

    ZHOU Guoliang, ZHANG Jianyun, LIU Jiufu, et al. Variational analysis of the relationship between wind and pressure of tropical cyclones in Northwest Pacific[J]. Advances in Water Science, 2011, 22(6): 750-755. (in Chinese)
    [7]
    孙全德, 焦瑞莉, 夏江江, 等. 基于机器学习的数值天气预报风速订正研究[J]. 气象,2019,45(3):426-436. (SUN Quande, JIAO Ruili, XIA Jiangjiang, et al. Adjusting wind speed prediction of numerical weather forecast model based on machine learning methods[J]. Meteorological Monthly, 2019, 45(3): 426-436. (in Chinese) doi: 10.7519/j.issn.1000-0526.2019.03.012

    SUN Quande, JIAO Ruili, XIA Jiangjiang, et al. Adjusting wind speed prediction of numerical weather forecast model based on machine learning methods[J]. Meteorological Monthly, 2019, 45(3): 426-436. (in Chinese) doi: 10.7519/j.issn.1000-0526.2019.03.012
    [8]
    钱斌凯, 何彩芬, 金炜, 等. 基于支持向量机的多因子风速预测[J]. 宁波大学学报(理工版),2018,31(3):14-19. (QIAN Binkai, HE Caifen, JIN Wei, et al. Multi-factors wind speed forecasting based on support vector machine[J]. Journal of Ningbo University (Natural Science & Engineering Edition), 2018, 31(3): 14-19. (in Chinese)

    QIAN Binkai, HE Caifen, JIN Wei, et al. Multi-factors wind speed forecasting based on support vector machine[J]. Journal of Ningbo University (Natural Science & Engineering Edition), 2018, 31(3): 14-19. (in Chinese)
    [9]
    许立兵, 孔扬, 周峥, 等. 基于机器学习的风场预报订正方法研究[J]. 陕西气象,2023(1):15-20. (XU Libing, KONG Yang, ZHOU Zheng, et al. Research on the method of wind field forecast correction based on machine learning[J]. Journal of Shaanxi Meteorology, 2023(1): 15-20. (in Chinese) doi: 10.3969/j.issn.1006-4354.2023.01.003

    XU Libing, KONG Yang, ZHOU Zheng, et al. Research on the method of wind field forecast correction based on machine learning[J]. Journal of Shaanxi Meteorology, 2023(1): 15-20. (in Chinese) doi: 10.3969/j.issn.1006-4354.2023.01.003
    [10]
    任萍, 陈明轩, 曹伟华, 等. 基于机器学习的复杂地形下短期数值天气预报误差分析与订正[J]. 气象学报,2020,78(6):1002-1020. (REN Ping, CHEN Mingxuan, CAO Weihua, et al. Error analysis and correction of short-term numerical weather prediction under complex terrain based on machine learning[J]. Acta Meteorologica Sinica, 2020, 78(6): 1002-1020. (in Chinese) doi: 10.11676/qxxb2020.060

    REN Ping, CHEN Mingxuan, CAO Weihua, et al. Error analysis and correction of short-term numerical weather prediction under complex terrain based on machine learning[J]. Acta Meteorologica Sinica, 2020, 78(6): 1002-1020. (in Chinese) doi: 10.11676/qxxb2020.060
    [11]
    ATKINSON G D, HOLLIDAY C R. Tropical cyclone minimum sea level pressure/maximum sustained wind relationship for the western North Pacific[J]. Monthly Weather Review, 1977, 105(4): 421-427. doi: 10.1175/1520-0493(1977)105<0421:TCMSLP>2.0.CO;2
    [12]
    KE G, MENG Q, FINLEY T, et al. LightGBM: A highly efficient gradient boosting decision tree[C/OL]∥Advances in Neural Information Processing Systems. Curran Associates, Inc. , 2017.
    [13]
    BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32. doi: 10.1023/A:1010933404324
    [14]
    ALAMSYAH N, BUDIMAN B, YOGA T P, et al. XGBoost hyperparameter optimization using RandomizedsearchCV for accurate forest fire drought condition prediction[J]. Jurnal Pilar Nusa Mandiri, 2024, 20(2): 103-110. doi: 10.33480/pilar.v20i2.5569
    [15]
    BERGSTRA J, BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13: 281-305.
    [16]
    RODRIGUEZ J D, PEREZ A, LOZANO J A. Sensitivity analysis of k-fold cross validation in prediction error estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 569-575. doi: 10.1109/TPAMI.2009.187

Catalog

    Article views PDF downloads Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return