Page 84 - 2023年第54卷第11期
P. 84

WRF?WRF - Hydrocoupledstreamflowforecastingbasedonreal - timeupdatingusingLSTM

                                                                1
                                                                             2
                                                    2
                                          1,2
                                                                                         1
                               LIUYuchen ,LIUJia,LIULusan,LIChuanzhe,WANGYu
                                  (1.ChineseResearchAcademyofEnvironmentalSciences,Beijing 100012,China;
                                  2.StateKeyLaboratoryofSimulationandRegulationofWaterCycleinRiverBasin,
                                 ChinaInstituteofWaterResourcesandHydropowerResearch,Beijing 100038,China)
                  Abstract:InordertoimprovetherunoffpredictionperformanceoftheWRF?WRF - Hydrocoupledatmospheric -
                  hydrologicsystemsandreducetheerrorsinpeaktimeandfloodpeakflowprediction ,thisstudyusesvariationalda
                  taassimilationtechnologytoreducetherainfallpredictionerror,atthesametime,areal - timecorrectionstudyon
                  therunoffpredictionprocessoftheWRF?WRF - Hydrosystem isconductedusingthelongshort - term memory
                  (LSTM),andcomparethereal - timecorrectionresultswiththeautoregressivemovingaveragemodel(ARMA).
                  TheresearchresultsindicatethatdataassimilationtechnologycaneffectivelyimprovetheaccuracyofWRFmodel
                  rainfallpredictionandreducetheinputerrorofWRF - Hydromodel ,buttheaccuracyofrunoffpredictionstill
                  needstobeimproved.Comparingthereal - timecorrectionresultsofLSTM andARMAmodelsforrunoffforecas
                  ting ,itwasfoundthatduringthefirstthreehoursoftheforesightperiod,theperformanceofthetwomodelsisba
                  sicallysimilarofsmallwatershedsinsemihumidandsemi - aridmountainousareasinnorthernChina.Exceptfor
                  Event4,theattenuationratesofLSTMandARMAmodelsinthethreehoursoftheforesightperiodare2.04~23.08
                  and9.18~36.47 ,respectively.Astheforesightperiodextends,thedecayrateofLSTM runoffpredictionaccuracy
                  isgenerallyslowerthantheARMAmodel ,andthepredictioneffectisbetterthantheARMAmodel.
                  Keywords:LSTM;real - timeupdating;WRF?WRF - Hydro;runoffforecast;dataassimilation


                                                                                    (责任编辑:韩 昆)


              (上接第 1333页)
                         Reservoiroutflowsimulationmodelbasedonreservoirtargetcapacitycurve

                          SHUPeng,XIONGLihua,CHENJie,YINJiabo,CHENGLei,ZHOUYanlai
                     (StateKeyLaboratoryofWaterResourcesandHydropowerEngineeringScience,WuhanUniversity,Wuhan 430072,China)


                  Abstract:Withthecontinuousconstructionofreservoirs,theimpactofreservoirsonthewatercycleismoreand
                  moresignificant ,andtheoutflowprocessofreservoirshasbecomeanimportantpartofthelandwatercycle.In
                  ordertosimulatetheimpactofReservoironwatercirculation ,ReservoirOutflow SimulationModel(ROSM)
                  shouldbeconstructedtosimulatetheoutflowofreservoir.However,thecurrentproposedROSMshaveweakgen
                  eralityandareonlyapplicabletoreservoirswithpresetoperationmode.Inthispaper ,itisassumedthatthegoal
                  reservoircapacityatvarioustimesoftheyearformsaTargetCapacityCurve (TCC).ThegeneralityofROSM can
                  beimprovedbysettingdifferentTCCsfordifferentreservoirs.Twomodelstructuresareproposedtoconsiderthe
                  influenceofTCConreservoirdischargefromtwoaspects :(1)Thereservoirtendstostorewaterandtheoutflow
                  decreasesintheseasonwithhighertargetstoragecapacity,whilethereservoirtendstoreleasewaterandtheout
                  flowincreasesintheseasonwithlowertargetstoragecapacity.(2)Theoutflowofthereservoirshouldmakethe
                  actualwaterstorageclosetothetargetstoragecapacity.Accordingtothetwomodelstructures,fourkindsofTCC
                  - basedROSM wereconstructed ,andthecommonROSM wereappliedto26reservoirsintheYangtzeRiver,
                  PearlRiverandYellowRiverbasins.Theresultsshowedthat:(1)theperformanceoftheoutflowsimulationand
                  waterstoragesimulationoftheROSM consideringthetwomodelstructureswasoptimal ,indicatingthatthestruc
                  tureofthetwomodelswasreasonableandeffective ;(2)ConsideringthatthesimulationaccuracyofTCCROSM
                  inmulti - yearandannualregulationreservoirsisfarhigherthanthatofotherROSM ,itindicatesthatTCCcanef
                  fectivelyimprovethesimulationaccuracyofthesetwotypesofreservoirsandimprovetheversatilityofROSM.
                  Keywords:reservoiroutflow;simulationmodel;reservoirstorage;reservoirtargetcapacitycurve


                                                                                    (责任编辑:于福亮)

                —  1 3 6 —
                     4
   79   80   81   82   83   84   85   86   87   88   89