LSTM和EnKF在農(nóng)業(yè)土壤降雨徑流模擬中的應(yīng)用

打開文本圖片集

中圖分類號：P333.1 文獻標(biāo)識碼：A文章編號：0439-8114（2025）05-0070-10DOI：10.14088/j.cnki.issn0439-8114.2025.05.011開放科學(xué)（資源服務(wù)）標(biāo)識碼（OSID）：

Application of LSTM and EnKF methods in agricultural soil rainfall-runoff simulation

LINLin 1 ，GAO Zhao-tian1，DINGYi-jia1，HU Xiao-long1，ZHANG Zhong-bin2 （1.Schoolof Water Resources and Hydropower Engineering，Wuhan University，Wuhan 43oo72，China; 2.Instituteof Soil Science，ChineseAcademyof Sciences，Nanjing211135，China）

Abstract：Terelatioshipetwenrainfallandrunoffisofgreatsgnificaceforteallcationofwaterresourcsandtheprotetionof waterandlandresousiagriculuralareas，utitisfult todealwithteainfall-unofprossunderdiferentlndueypes insmall watersheds.Thelongshort-termmemorymodel（LSTM）andtheXin'anjiangmodelcombinedwithensembleKalmanfilter （EnKF）technologywereusedtoexplorethesimulatioefectivenessofdata-drivenmachinelearning（ML）modelonrainfal-runoff processunderdiferentlandusepaterns，andthesimulationefectiveness wascomparedwiththatofSWAThydrological model.The estimationefectivenesofEnKFonhdrologicalparametersensemblesinheXin'njangmodelandthepattsoffilestiated parameters werestudied，andterunoffprocessesfordiferenagriculturallndusetypesbasedonthecalibratedparametersweresimulated.Theresultsshowedthattherunoffvaluewaseasiertolearninthecaseofhighrunoffwithaslightlysmallslopeandthelowrunoffprocess ithalargeslope.ThesimulationaccuracyandstabilityoftheSWATmodelwerenotasgodas thoseoftheLSTMmodel， butSWATmodelcouldreflctthelocalsoilhydrologicalconditionstoacertainextent，whichwasconvenientforgeneticanalyis.The EnKFtechologyhadthefunctionsofparameterupdateandparameterestimation，whchcouldoptimizetheunoffsimulatiofectiveness of the Xin'anjiang model.

KeyWords：ainfallrunofsiulation；datadriven;dataassiilation；LSTM;EnKF;Xinaangmodel;landusepae;ptiie forecasting

中國南方小流域的紅壤區(qū)生態(tài)系統(tǒng)面臨著嚴(yán)重的水土流失、土壤酸化、肥力退化、季節(jié)性干旱及土壤污染等問題[12]，是由于該區(qū)域降雨時空分布不均勻以及不合理的開發(fā)利用，因此研究區(qū)域內(nèi)氣候、植被、土壤等對降雨徑流有影響的因素成為土壤生態(tài)環(huán)境等領(lǐng)域的熱門話題

隨著科技的不斷發(fā)展，數(shù)據(jù)處理與機器學(xué)習(xí)等技術(shù)提高了各類模型的精度與構(gòu)建效率。（剩余10061字）