Page 220 - 《水资源与水工程学报》2025年第2期
P. 220

1
             2 6                      & ' ( ) & * + , -                 2025 $
            »¼‘‘óV; n, ‰¡üoQ˜Ì>¡ 4 ûí                           2021,385:114863.
            %»¼‘È-, È-í%¡5üoQ˜T‘’                            [9]FATHOLOLOUMIS,VAEZIAR,ALAVIPANAHSK,et
            žyXYÈZ。šÎ$‰H‘>d‚ƒ, A_                               al.Effectofmultitemporalsatelliteimagesonsoilmoisture
                                                                  predictionusingadigitalsoilmappingapproach [J].Geo
            ˜‘í%T, ÒÓ。毖ÈZo~Q˜T
                                                                  derma ,2021,385:114901.
            ‘’Þg, ÃV¡o~Q˜»¼°OTQ©
                                                               [10]WEIXin,ZHANGLulu,YANGHaoqing,etal.Machine
            †½, ÀóVɉ¡NTBXí%, K¾u!NªT
                                                                   learningforporewaterpressuretimeseriesprediction:
            ()RÝ。
                                                                   applicationofrecurrentneuralnetworks[J].Geoscience
            6 f i                                                  Frontiers,2021,12(1):453467.
                                                               [11]HEDDAM S.3newformulationforpredictingsoilmois
                 (1) 4WpPo~Q˜T„P>?+e7æL                            turecontentusingonlysoiltemperatureaspredictor:mul
            [.T, ´+•–™œš›$g@le՟,                                tivariateadaptiveregressionsplinesversusrandomforest,
            æ…ÆÑg、 6Мg、 jaJÔI.。                                   multilayerperceptronneuralnetwork,M5Tree,andmulti
                 (2) Y‰}gT 4 ûo(20、40、60、80cm)                   plelinearregression [J].WaterEngineeringModelingand
                                                                   MathematicTools ,2021:4562.DOI:10.1016/B9780
            ŠBÌ>ܔ†æ 4 û„÷Bg(1、12、24、48h),
                                                                   1282064417.00027X.
            (RÁæÈZí%‘’ÞgJ_˜‘’ÒÓÈç‘
                                                               [12]AHMEDAAM,DEORC,GHAHRAMANIA,etal.
            NLVTyo。
                                                                   LSTMintegratedwithBoruta-randomforestoptimiserfor
                 ( 3) Fa5| éՄÌ>óVT LSTM-1
                                                                   soilmoistureestimationunderRCP4.5andRCP8.5global
            í%, BX LSTMí%º¡oU 12、24、48h T‘’                        warmingscenarios [J].StochasticEnvironmentalResearch
                 2
            !,R †xȝ‘ 2.42%、5.71%、12.26%; (í%                      andRiskAssessment,2021,35(9):18511881.
            Ï:¯õÅÉ·Ûv‘’4WpP=âüoQ˜                             [13]ZHANGFangfang,WUShiwen,LIUJie,etal.Predic
            ˜™。                                                    tingsoilmoisturecontentoverpartiallyvegetationcovered
                                                                   surfacesfrom hyperspectraldatawithdeeplearning [J].
            ÕÖKL:                                                  SoilScienceSocietyofAmericaJournal ,2021,85(4):
            [1]îö3, _!d, 1—ÿ, Q. 4WznÝûÂPIMN                       9891001.
                OPKLTIM,> .[J]. F[#$Zš,2018,34                 [14]PONKINAE,ILLIGERP,KROTOVAO,etal.DoARMA
                (11):96104.                                       modelsprovidebettergapfillingintimeseriesofsoiltempera
            [2]$ `, é ¦, aêf, Q. ‰}Žv“ÊbSo~I†„                     tureandsoilmoisture ?thecaseofarablelandintheKulunda
                …†‡Q©[J]. o~Zš,2021,58(6):14231435.               Steppe ,Russia[J].Land,2021,10(6):579.
            [3]í |, j !, ՐH, Q. lnh!qFGo~I†(.                 [15]CARRANZAC,NOLETC,PEZIJM,etal.Rootzone
                «¦„PQ©[J]. o~,2019,51(2):390398.                  soilmoistureestimationwithrandomforest[J].Journalof
            [4]î×2, 1^., ç#Ì, Q. o~I†ÑHQ©„.(                       Hydrology ,2021,593:125840.
                )Ûe[J]. o~Zš,2019,56(1):2335.                 [16]HANH,CHOIC,KIMJ,etal.Multipledepthsoilmois
            [5]ZHANGQiuru,SHILiangsheng,HOLZMANM,etal.A            tureestimatesusingartificialneuralnetworkandlongshort
                dynamicdatadrivenmethodfordealingwithmodelstruc  termmemorymodels [J].Water,2021,13(18):2584.
                turalerrorinsoilmoisturedataassimilation [J].Advances  [17]ADEYEMIO,GROVEI,PEETSS,etal.Dynamicneural
                inWaterResources,2019,132:103407.                  networkmodellingofsoilmoisturecontentforpredictiveirri
            [6]ABIOYEEA,ABIDINMSZ,MAHMUDMSA,etal.IoT              gationscheduling [J].Sensors,2018,18(10):3408.
                basedmonitoringanddatadrivenmodellingofdripirrigation  [18]FILIPOVI N,BRDARS,MIMI G,etal.Regionalsoil
                systemformustardleafcultivationexperiment[J].Information  moisturepredictionsystembasedonlongshorttermMemory
                ProcessinginAgriculture ,2021,8(2):270283.        network[J].BiosystemsEngineering,2022,213:3038.
            [7]ADABH,MORBIDELLIR,SALTALIPPIC,etal.Ma          [19]ELSAADANIM,HABIBE,ABDELHAMEEDAM,et
                chinelearningtoestimatesurfacesoilmoisturefromremote  al.Assessmentofaspatiotemporaldeeplearningapproach
                sensingdata [J].Water,2020,12(11):3223.            forsoilmoisturepredictionandfillingthegapsinbetween
            [8]TANEJAP,VASAVAHK,DAGGUPATIP,etal.Multi             soilmoistureobservations [J].FrontiersinArtificialIn
                algorithmcomparisontopredictsoilorganicmatterandsoil  telligence ,2021,4:636234.
                moisturecontentfrom cellphoneimages [J].Geoderma,  [20]Ò!G, /Gï, a ò, Q. cñëRI¬¬èºB
   215   216   217   218   219   220   221   222   223   224   225