基于多种神经网络的风暴潮增水预测方法的比较分析

详细信息    查看全文 | 推荐本文 |

英文篇名：Comparative analysis of storm surge water prediction methods based on multiple neural networks 作者：薛明 ; 李醒飞 ; 成方林 英文作者：XUE Ming;LI Xing-fei;CHENG Fang-lin;School of Precision Instrument and Optoelectronics Engineering, Tianjin University;National Ocean Technology Centre; 关键词：风暴潮增水 ; 预测 ; BP神经网络 ; 小波神经网络 ; 递归神经网络 英文关键词：storm surge;;prediction;;BP neural network;;wavelet neural network;;recurrent neural network 中文刊名：HUTB 英文刊名：Marine Science Bulletin 机构：天津大学精密仪器与光电子工程学院;国家海洋技术中心; 出版日期：2019-06-15 出版单位：海洋通报 年：2019 期：v.38;No.224 语种：中文; 页：HUTB201903007 页数：6 CN：03 ISSN：12-1076/P 分类号：53-58

摘要

简要介绍了利用BP神经网络、小波神经网络、递归神经网络进行风暴潮增水值预测的原理。选取广东省珠江口以南的阳江站2017年风暴潮增水数据进行测试。结果表明,三种神经网络方法针对阳江地区风暴潮增水的预测均具有可靠性和实用性。以当前增水值为输入量的单因子模型更能反映真实风暴潮增水趋势,而从增水极值预测的准确性来看,以台风风力、气压、风向等相关参数为输入量的多因子模型优于单因子模型。BP神经网络更适用于多因子长时间预测,小波神经网络在单因子短时间预测上准确性更高,递归神经网络预测值与实测值相关性更强。在工程运用中,需根据地域时空特点、数据资料的丰富度与预测值评估指标选择合适的方法。
        The principle of using BP neural network, wavelet neural network and recurrent neural network to predict the storm surge water increase value are briefly introduced. The 2017 storm surge water increase data of the Yangjiang station of the Pearl River Estuary in Guangdong Province was selected for testing. The results show that the three neural network methods are reliable and practical for the prediction of storm surge water increase in Yangjiang area. The single factor model with the current water added value is more capable to reflect the true storm surge water increase trend. From the accuracy of the prediction of the maximum value of water increase, the multi-factor model with input parameters such as typhoon wind,air pressure and wind direction is better than the single factor model. BP neural network is more suitable for multi-factor long time prediction. The wavelet neural network has higher accuracy in single-factor short-time prediction, and the recurrent neural network prediction value is more correlated with the measured value. In the engineering application, it is necessary to select an appropriate method according to the spatial and temporal characteristics of the region, the richness of the data, and the predictive value evaluation index.

引文

Botvinick M M,Plaut D C,2006.Short-term memory for serial order:a recurrent neural network model.Psychological review,113(2):201-233.
    Kim S Y,Shiozaki S,Matsumi Y,et al,2012.A study of a real-time storm surge forecast system using a neural network at the Sanin Coast,Japen//Oceans.Hampton Road,VA:IEEE,1-7.
    Lee T L,2006.Neural network prediction of a storm surge.Ocean engineering,33(3):483-494.
    Sovzil D,Kvasnicka V,Pospichal J,et al,1999.Introduction to multilayer feed-forword neural networks.Chemometrics and intelligent laboratory systems,39(1):53-62.
    蔡煜东,姚林生,1994.预报台风风暴潮极值的人工神经网络方法.海洋预报,11(1):77-81.
    冯士筰,1982.风暴潮导论.北京:科学出版社,1-30.
    谷川,王丽华,万军,2007.基于小波和神经网络的潮汐分析和预测//第四届长三角论坛---测绘分论坛论文集,60-63.
    国家海洋信息中心,2016.2017潮汐表.第3册,台湾海洋至北部湾.北京:海洋出版社,5.
    侯京明,于福江,原野,等,2011.影响我国的重大台风风暴潮时空分布,海洋通报,30(5):535-539.
    雷森,史振威,石天阳,等,2017.基于递归神经网络的风暴潮增水预测.智能系统学报,12(5):640-644.
    聂源,李铖,李琪,2013.国内外风暴潮预报研究进展.地球,(7):312-313.
    田景文,高美娟,2006.人工神经网络算法研究及运用.北京:北京理工大学出版社.
    王恺,杨巨峰,王立,等,2008.人工神经网络泛化问题研究综述.计算机应用研究,25(12):3525-3530,3533.
    王如云,雷磊,占飞,等,2014.基于高低潮的风暴潮增水人工神经网络预报模型.海洋预报,31(6):23-27.
    王喜年,2001.风暴潮预报知识讲座.海洋预报,18(3):60-64.
    薛彦广,沙文钰,徐海斌,等,2005.人工神经网络在风暴潮增水预报中的运用.海洋预报,22(2):33-37.
    杨万康,杨青莹,伊小飞,等,2017.典型风暴潮增水特征与机理研究,海洋通报,36(5):532-537.