深圳大鹏湾波高实时预报  

Real time wave height forecasting in Mirs Bay of Shenzhen

作　　者：方莹[1] 毛献忠[1] 

机构地区：[1]清华大学深圳研究生院海洋学部,广东深圳518055

出　　处：《海洋预报》2016年第3期34-40,共7页Marine Forecasts

基　　金：国家自然科学基金项目(41176001);深圳市科技项目(GJHS20120702112942334)

摘　　要：采用非线性自回归神经网络与带外部输入的非线性自回归神经网络建立了深圳大鹏湾浮标站有效波高实时预报模型,分别预报了湾口与大梅沙两处浮标站点的3 h、6 h与12 h有效波高。预报结果显示:湾口浮标处3 h、6 h预报结果与实测值符合较好,相对误差在10%以内,相关系数在0.8以上;大梅沙浮标处波高3 h预报绝对误差在0.10 m以内,相关系数在0.6以上。Nonlinear autoregressive network （NAR） and nonlinear autoregressive network with exogenous inputs （NARX） are applied to forecast the real-time wave height at buoys in Mirs Bay of Shenzhen. The wave heights for the next 3, 6 and 12h at two buoy stations are forecasted. The result shows that the forecasting of wave height at Wankou station agrees well with observations, with the relative error of less than 15% and the correlation coefficient of greater than 0.8; the errors of 3, 6h forecasting at Dameisha Station are less than 0.10m, and the correlation coefficients are more than 0.6.

关 键 词：大鹏湾 波高 NAR神经网络 NARX神经网络 实时预报 

分 类 号：P731.22[天文地球—海洋科学]