本文選題：數(shù)值預(yù)報(bào) + 釋用　； 參考：《海洋與湖沼》2016年06期

【摘要】：為了提高近岸精細(xì)化海溫預(yù)報(bào)精度,利用神經(jīng)網(wǎng)絡(luò)方法,分析了海溫?cái)?shù)值預(yù)報(bào)及觀測(cè)數(shù)據(jù)在釋用中的作用,研究了定點(diǎn)近岸海溫影響因子的最優(yōu)配置方案,建立了定點(diǎn)海溫精細(xì)化數(shù)值預(yù)報(bào)釋用模型,評(píng)估了釋用模型性能。誤差分析結(jié)果顯示,數(shù)值海溫產(chǎn)品及其觀測(cè)在建模中起到了降低和穩(wěn)定模型誤差的作用;釋用模型將定點(diǎn)數(shù)值預(yù)報(bào)的誤差從2.2°C減少至0.7°C;預(yù)報(bào)誤差較調(diào)訓(xùn)誤差略高,但考慮到預(yù)報(bào)誤差的穩(wěn)定性,數(shù)值釋用與人工經(jīng)驗(yàn)預(yù)報(bào)水平持平,因此,該方法具有十分廣闊的拓展空間和應(yīng)用前景。
[Abstract]:In order to improve the precision of inshore fine SST prediction, the function of SST numerical forecast and observation data in interpretation is analyzed by using neural network method, and the optimal configuration scheme of the influence factors of fixed NLS is studied. A precise numerical prediction model of SST is established and the performance of the model is evaluated. The results of error analysis show that the numerical SST products and their observations play a role of reducing and stabilizing the model errors in modeling, that the numerical prediction errors of fixed points are reduced from 2.2 擄C to 0.7 擄C, and that the prediction errors are slightly higher than those of training. However, considering the stability of prediction error, the numerical interpretation level is equal to that of artificial experience, so this method has a very broad space and application prospect.
【作者單位】： 國(guó)家海洋環(huán)境預(yù)報(bào)中心;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目,41222038號(hào) 海洋公益性行業(yè)科研專項(xiàng)經(jīng)費(fèi)項(xiàng)目,201305031號(hào)
【分類號(hào)】：P731.31
，

本文編號(hào)：2018119