苗庆生,徐珊珊,杨锦坤,杨杨,刘玉龙,余璇

• 1:国家海洋信息中心
• 2:上海大学

摘要(Abstract)：

利用长短期记忆神经网络(LSTM)模型强大的长短期记忆能力，建立厦门风暴潮增水预报的人工神经网络模型。利用信息流理论确定了影响增水的10种因子，分别利用不同因子组合测试了不同模型的表现，确定了表现最佳的因子组合。基于此因子组合，对比了LSTM模型和常用的BP神经网络模型、SVM模型和线性回归模型，确定了LSTM模型在风暴潮增水上的优势。基于LSTM最佳预测模型预测了1、2、3及6 h风暴潮增水值，并基于三种不同台风路径分析了模型的平均绝对误差、相关系数、有效系数和极值偏差指标。结果显示，LSTM模型在预报风暴潮短期增水有很高精度，可为防灾减灾提供辅助和参考。

关键词(KeyWords)： 风暴潮;信息流;长短期记忆神经网络(LSTM);神经网络;预报

Abstract:

Keywords:

基金项目(Foundation): 国家重点研究发展计划项目(2016YFC1401900)资助~~

作者(Author): 苗庆生,徐珊珊,杨锦坤,杨杨,刘玉龙,余璇

DOI: 10.16441/j.cnki.hdxb.20210167

参考文献(References)：

• [1] Doodson A T.Tides and storm surges in a long uniform gulf[J].Proc Math Phys Eng Sci,1956,237:325-343.
• [2] Webster P J,Holland G J,Curry J A,et al.Changes in tropical cyclone number,duration,and intensity in a warming environment[J].Science,2005,309:1844-1846.
• [3] Emanuel K A.Increasing destructiveness of tropical cyclones over the past 30 years[J].Nature,2005,436:686-688.
• [4] 朱星桦.基于改进联合概率模型的厦门岛极端水位预测研究[D].南京：东南大学，2018.Zhu Xinghua.Estimating Extreme Water Levels with Joint Probability Optimal Sampling Method in Xiamen Island[D].Nanjing:Southeast University,2018.
• [5] Chao W T,Young C C,Hsu T W,et al.Long-lead-time prediction of storm surge using artificial neural networks and effective typhoon parameters:Revisit and deeper insight[J].Water,2020,12(9):1-24.
• [6] Conner W C,Kraft K H,Harris D L.Empirical methods for forecasting the maximum storm tide due to hurricanes and other tropical storms[J].Monthly Weather Review,1957,85:113-116.
• [7] Welander P.Numerical predictions of storm surges[J].Advances in Geophysics,1961,8:315-379.
• [8] Platzman G W.The dynamical prediction of wind tides on Lake Erie[J].Meteorol Monogr,1963,4:1-44.
• [9] Jelesnianski C P.A numerical calculation of storm tides induced by a tropical storm impinging on a continental shelf[J].Monthly Weather Review,1965,93:343-358.
• [10] Holland G J.An analytic model of the wind and pressure profiles in hurricanes[J].Monthly Weather Review,1980,108:1212-1218.
• [11] Weserink J J,Luettich R A,Baptista A M,et al.Tide and storm surge predictions using a finite element model[J].Journal of Hydraulic Engineering,1992,118:1373-1390.
• [12] Shen J,Zhang K,Xiao C,et al.Improved prediction of storm surge inundation with a high-resolution unstructured grid model[J].Journal of Coastal Research,2006,22:1309-1319.
• [13] Kim S Y,Yasuda T,Mase H.Numerical analysis of effects of tidal variations on storm surges and waves[J].Applied Ocean Research,2008,30:311-322.
• [14] Chen W B,Liu W C,Hsu M H.Computational investigation of typhoon-induced storm surges along the coast of Taiwan[J].Natural Hazards,2012,64:1161-1185.
• [15] Wu G,Shi F,Kirby J T,et al.Modeling wave effects on storm surge and coastal inundation[J].Coastal Engineering,2018,140:371-382.
• [16] Dietrich J C,Zijlema M,Westerink J.et al.Modeling hurricane waves and storm surge using integrally coupled scalable computations[J].Coastal Engineering,2011,58:45-65.
• [17] Torres M J,Hashemi M R,Hayward S,et al.Role of hurricane wind models in accurate simulation of storm surge and waves[J].Journal of Waterway Port Coastal and Ocean Engineering,2019,145(1):04018039.
• [18] Dietrich J C,Zijlema M,Westerink J,et al.Modeling hurricane waves and storm surge using integrally coupled scalable computations[J].Coastal Engineering,2011,58:45-65.
• [19] Kohno N,Dube S K,Entel M,et al.Recent progress in storm surge forecasting[J].Tropical Cyclone Research and Review,2018,7:128-139.
• [20] Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagating errors[J].Nature,1986,323:533-536.
• [21] Bajo M,Umgiesser G.Storm surge forecast through a combination of dynamic and neural network models[J].Ocean Model,2010,33:1-9.
• [22] Erdil A,Arcaklioglu E.The prediction of meteorological variables using artificial neural network[J].Neural Computing & Applications,2013,22:1677-1683.
• [23] Young C C,Liu W C.Prediction and modelling of rainfall-runoff during typhoon events using a physically-based and artificial neural network hybrid model[J].Hydrologccal Sciences Journal,2015,60:2102-2116.
• [24] Young C C,Liu W C,Chang C E.Genetic algorithm and fuzzy neural networks combined with the hydrologic modeling system for forecasting watershed runoff discharge[J].Neural Computing & Applications,2015,26:1631-1643.
• [25] SK A,SP B,HM C.Artificial neural network-based storm surge forecast model:Practical application to Sakai Minato,Japan[J].Applied Ocean Research,2019,91:101871.
• [26] 卢君峰，李少伟，袁方超.基于BP神经网络的厦门沿海风暴潮预报应用[J].海洋预报，2016,33(4):9-16.Lu J F,Li S W,Yuan F C.Application of storm surge forecasting by BP artificial neural network off coast of Xiamen[J].Marine Forecasts,2016,33(4):9-16.
• [27] 李未，王如云，卢长娜，等.神经网络在珠江口风暴潮预报中的应用[J].热带海洋学报，2006(3):10-13.Li W,Wang R Y,Lu C N,et al.Forecast of storm surge in Zhujiang River estuary by means of artificial neural network[J].Journal of Tropical Oceanography,2006(3):10-13.
• [28] Deng L,Yu D.Deep learning:Methods and applications[J].Foundations and Trends in Signal Processing,2014,7(3/4):197-387.
• [29] Yang Y,Dong J,Sun X,et al.A CFCC-LSTM Model for sea surface temperature prediction[J].IEEE Geoence & Remote Sensing Letters,2017(2):1-5.
• [30] Zhang Q,Wang H,Dong J,et al.Prediction of sea surface temperature using long short-term memory[J].IEEE Geoscience and Remote Sensing Letters,2017,14(10):1745-1749.
• [31] 石绥祥，王蕾，余璇.长短期记忆神经网络在叶绿素a浓度预测中的应用[J].海洋学报，2020,42(2):134-142.Shi Suixiang,Wang lei,Yu Xuan,et al.Application of long term and short term memory neural network in prediction of chlorophyll a concentration[J].Haiyang Xuebao,2020,42(2):134-142.
• [32] Yang C H,Wu C H,Hsieh C M.Long short-term memory recurrent neural network for tidal level forecasting[J].IEEE Access,2020(99):1-13.
• [33] Jan C D,Tseng C M,Wang J S,et al.Empirical relation between the typhoon surge deviation and the corresponding typhoon characteristics:A case study in Taiwan[J].Journal of Marine Science & Technology,2006,11(3):193-200.
• [34] Yen P H,Jan C D,Lee Y P,et al.Application of Kalman filter to short-term tide level prediction[J].Journal of Waterway Port Coastal & Ocean Engineering,1998,122(5):226-231.
• [35] Doodson A T.Oceanic Tides.Advances in Geophysics[M].New York:Academic Press,1958:117-152.
• [36] Pan H,Lv X,Wang Y,et al.Exploration of tidal-fluvial interaction in the Columbia River Estuary using S_TIDE[J].Journal of Geophysical Research:Oceans,2018,123:6598-6619.
• [37] Pawlowicz R,Beardsley B,Lentz S.Classical tidal harmonic analysis including error estimates in MATLAB using T_TIDE[J].Computers & Geosciences,2002,28(8):929-937.
• [38] 许金电，郭小钢，黄奖.2006年夏季福建近海台风风暴潮特征分析[J].台湾海峡，2011,30(4):473-482.Xu J D,Guo X G,Huang J.Analysis of the characteristics of typhoon storm surges in Fujian offshore area during 2006 summer[J].Journal of Oceanography in Taiwan Strait,2011,30(4):473-482.
• [39] 黄森军.浙江近海台风暴潮及冲淤研究[D].杭州：浙江大学，2017.Huang Senjun.Research on Storm Surge and Erosion and Deposition of Typhoon Offshore in Zhejiang[D].Hangzhou:Zhejiang University,2017.
• [40] Liang X S.Information flow and causality as rigorous notions abinitio[J].Physical Review E,2015,94(5):1-49.
• [41] Liang X San,Entropy evolution and uncertainty estimation with dynamical systems[J].Entropy,2014,16:3605-3634.
• [42] 张文舟，胡建宇，商少平，等.福建沿海风暴潮特征的分析[J].海洋通报，2004,23(3):12-19.Zhang W Z,Hu J Y,Shang S P,et al.On the characteristics of storm surges along Fujian Coast[J].Marine Science Bulletin,2004,23(3):12-19.
• [43] 张莉，商少平，谢燕双，等.基于有限元法的福建沿岸天文潮-风暴潮耦合预报模式研究[J].应用海洋学报，2016,35(2):256-265.Zhang L,Shang S P,Xie Y S,et al.A tide-storm surge coupled model based on finite element method for Fujian coast[J].Journal of Applied Oceanography,2016,35(2):256-265.

文章评论(Comment)：