【摘要】：針對(duì)冗余訓(xùn)練樣本會(huì)降低BMA參數(shù)求解效率與精度問題,本文提出在BMA運(yùn)算之前采用k-最近鄰(k-nearest neighbor)算法篩選有價(jià)值訓(xùn)練樣本,并用于BMA參數(shù)求解的改進(jìn)模型。模擬試驗(yàn)在淮河王家壩站進(jìn)行,分別以k-最近鄰篩選、不篩選兩種方案為BMA提供訓(xùn)練樣本,統(tǒng)計(jì)分析兩種方案中王家壩站流量模擬結(jié)果,評(píng)價(jià)BMA改進(jìn)法的性能。模擬結(jié)果顯示,采用k-最近鄰樣本篩選方法后,BMA模型對(duì)洪水過程以及洪峰的預(yù)報(bào)精度提升明顯;概率預(yù)報(bào)結(jié)果的離散程度降低的同時(shí),可靠性程度獲得提升。k-最近鄰樣本篩選方法的引入,能夠有效去除BMA模型訓(xùn)練樣本中的冗余數(shù)據(jù),以少量的樣本獲得更可靠的模型參數(shù),改善集合預(yù)報(bào)性能。
[Abstract]:In view of the problem that redundant training samples can reduce the efficiency and precision of BMA parameter solving, this paper presents an improved model of selecting valuable training samples by using k- nearest neighbor (k-nearest neighbor) algorithm before BMA operation, which can be used to solve BMA parameters. The simulation test was carried out at the Wangjiaba Station of Huaihe River. The two schemes were screened by the nearest neighbor, and the two schemes were not screened to provide training samples for the BMA. The flow simulation results of the Wangjiaba Station in the two schemes were statistically analyzed, and the performance of the improved BMA method was evaluated. The simulation results show that the accuracy of BMA model for flood process and Hong Feng is improved obviously, and the dispersion of probabilistic forecast results is reduced. The introduction of K-nearest neighbor sample screening method can effectively remove redundant data from training samples of BMA model, obtain more reliable model parameters with a small number of samples, and improve the performance of ensemble prediction.
【作者單位】： 淮河水利委員會(huì)水文局(信息中心);河海大學(xué)水文水資源學(xué)院;
【基金】：國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2016YFC0400909) 國(guó)家自然科學(xué)基金項(xiàng)目(41130639,51179045,41101017,41201028)
【分類號(hào)】：P338

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 盧迪;彭勇;徐煒;周惠成;;氣象集合預(yù)報(bào)在水文領(lǐng)域中的應(yīng)用研究進(jìn)展[J];南水北調(diào)與水利科技;2014年02期

2 陸桂華;吳娟;吳志勇;;水文集合預(yù)報(bào)試驗(yàn)及其研究進(jìn)展[J];水科學(xué)進(jìn)展;2012年05期

3 李巖;胡軍;王金星;劉松;章四龍;;河流集合預(yù)報(bào)方法(ESP)在水資源中長(zhǎng)期預(yù)測(cè)中的應(yīng)用研究[J];水文;2008年01期

4 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 包紅軍;趙琳娜;梁莉;;基于水文集合模式的流域洪澇預(yù)報(bào)技術(shù)[A];第十四屆中國(guó)科協(xié)年會(huì)第14分會(huì)場(chǎng)：極端天氣事件與公共氣象服務(wù)發(fā)展論壇論文集[C];2012年

相關(guān)重要報(bào)紙文章 前1條

1 本報(bào)記者 張妍;為水庫(kù)蓄水提供決策依據(jù)[N];中國(guó)氣象報(bào);2011年

相關(guān)碩士學(xué)位論文 前1條

1 油芳芳;耦合ECMWF降雨集合預(yù)報(bào)的水庫(kù)優(yōu)化調(diào)度研究[D];大連理工大學(xué);2014年

，

本文編號(hào)：2283506