Page 88 - 《水资源与水工程学报》2023年第1期
P. 88

!34 " ! 1 #                       & ' ( ) & * + , -                               Vol.34No.1
               2023 $ 2 %               JournalofWaterResources&WaterEngineering                 Feb.,2023

            DOI:10.11705/j.issn.1672-643X.2023.01.10


                         '«´H:›H(”H|Vµ€:;


                                                   1,2         1,2        1,2
                                            Zmq , crs , Ztu
                           (1. õðÑÁ*3ie 12Xè%&el, 9õ ›È 712100;2. õðÑÁ*3ie
                                      špÑÒ1j%&IEn:;}~, 9õ ›È 712100)

                 A B: Ð=|S56̅Sqy¥Ûž、 Ñ҆®、 1rs¿]'):P^_。£Ì|S>X')ÍAö¿
                 ´–ösU´‰Š, È5ß±ª|S56éMž VMD-(CNN-LSTM,ELMAN)。³·h VMD§|S>X»
                 ­¾—«T»Ú, ¦6ÁëT»ÚÂU;á(SE), §`7»¾ÉK–‚ÎK»Ú; Æh CNN-LSTM
                 ž56ÉK»Ú, h ELMANž56‚ÎK»Ú; 8Ƨ56ÃÄ:ûk¨8®56ÃÄ。§ž€…m
                 'Sq‚vó)êùë–êí51U“ª|S56, ¦X CNN-LSTM、ELMAN、VMD-CNN-LSTMž56
                 ÃÄ·¸ÌÓX¡e。+^ÃijÅ: UUž56Ãč NSEáÖi… 0.99, š…`䝞, ³Å VMD-(CNN-
                 LSTM,ELMAN) ž')Íɍ56[¿, ހ…}"+^p|S56。
                 CDE: |S56; 껝T»­; µ“BC; m'Sq
                                +
                 FGHIJ:TV121 .4   KLMNO:A    KPQJ:1672643X(2023)01008407
                           Runoffpredictionmodeloffrequencydivisionbasedon
                                          variationalmodedecomposition

                                                                   1,2
                                                  1,2
                                 ZHANGXiaoxuan ,SONGSongbai ,ZHANGBinglin             1,2
                   (1.CollegeofWaterResourcesandArchitecturalEngineering,NorthwestA&FUniversity,Yangling712100,China;
                    2.KeyLaboratoryofAgriculturalSoilandWaterEngineeringinAridandSemiaridAreas,MinistryofEducation,
                                         NorthwestA&FUniversity,Yangling712100,China)
                 Abstract:Accuraterunoffpredictionisofgreatsignificanceforagriculturalirrigation,reservoirschedu
                 ling,floodcontrolanddisastermitigationinthebasin.Aimingatthestrongnonlinearityandnonstation
                 arityoftherunoffseries,ahybridmodelformonthlyrunoffprediction,VMD(CNN-LSTM,ELMAN),
                 isproposed.Firstly,VMDisusedtodecomposetherunoffsequenceintomultiplemodalcomponents,
                 andthesampleentropy(SE)ofeachmodalcomponentiscalculated,accordingtowhichthecompo
                 nentsaredividedintohighfrequencyandmediumlowfrequencycomponents.ThentheCNN-LSTM
                 modelisusedforthepredictionofhighfrequencycomponents ,theELMANmodelforthemediumlow
                 frequencycomponents.Finallythepredictionsresultsaresummedup.Themodelisthenappliedtothe
                 monthlyrunoffpredictionofBaimasiStationandHeishiguanStationinthemiddleandlowerreachesof
                 theYellowRiverBasin ,andthepredictionresultsareevaluatedcomparedwiththoseofCNN-LSTM,
                 ELMAN,VMD-CNN-LSTM models.ResearchresultsshowthattheNSEvaluesofthepredictionre
                 sultsofthismodelareallgreaterthan0.99 ,whichissuperiortoothermodels,indicatingthatthe
                 VMD-(CNN-LSTM,ELMAN)modelhashighpredictionaccuracyandcanbeappliedtoactual
                 monthlyrunoffpredictionofthebasin.
                 Keywords:runoffprediction;variationalmodedecomposition(VMD);neuralnetwork;theYellow
                 RiverBasin


                !"#$:20220619; %&#$:20220826
                '()*: 89œ*e„2./(52079110)
                +,-.: ˜½å(1999-), A, :q\hE, KG+^L, OPQR1U5ʵf+^。
                /0+,: òøæ(1965-), b, 9õïçE, FG, IJ, OPQRSq1UNX1U5Ê]µeIeX*+%o。
   83   84   85   86   87   88   89   90   91   92   93