基于iTransformer與LSTM模型融合的農(nóng)場氣溫多步預(yù)測

打開文本圖片集

關(guān)鍵詞：iTransformer;LSTM；模型融合；多特征；農(nóng)場氣溫；多步預(yù)測

中圖分類號：TP183 文獻(xiàn)標(biāo)識碼：A

文章編號：0439-8114（2025）05-0134-07

DOI：10.14088/j.cnki.issn0439-8114.2025.05.021 開放科學(xué)（資源服務(wù)）標(biāo)識碼（OSID）：

Multi-step temperature prediction for farms based on iTransformer and LSTM model fusion

XIE Qi， ZHANG Tai-hong，LIU Hai-peng

（Colegefftteala of Intelligent Agriculture，MinistryofEducation，Xinjiang Agricultural University，Urumqi830o52，China）

Abstract：Toadressthenonlinearandomplexcharacteristicsoffarmtemperaturedata，basedonmeteorologicalstationdatafrom HuaxingFarminChangji City，XinjiangUygurAutonomous Region，sevenfeaturesincludingtemperature，groundinfraredtemperature，dewpointtemperaturerelativehumidityaporpressure，stationpressure，andsea-levelpressurewereselectedasmodelinput features throughSpearancorelationanalysis，andomparativeanalsisascoductedamongtheiransformer-LSTodelras former model，LSTMmodel，iTransformermodel，andTransformer-LSTMmodel.TheresultsshowedthattheiTransformer-TM modelachievedthebestperformance.Comparedwiththeoptimal baselinemodeliTransformer，thismodelreducedtherootmean square error（RMSE）by 13.72% ，mean absolute error （ MAE ）by 14.12% ，and mean absolute percentage error （ MAPE ）by 13.61% TheiTransformer-LSTMmodelcouldefectivelyextracttime-series featurerepresentations，capturelong-termdependencies，and characterize globalaturesandcontextualinformation，makingitsuitableforulti-featureulti-steptimeseries temperatureprediction tasks.

Key Words：iTransformer;LSTM;model fusion；multi-feature; farm temperature；multi-step prediction

氣候變化可能引發(fā)極端天氣事件，如干旱、洪澇、低溫和霜凍，這些現(xiàn)象對農(nóng)業(yè)生產(chǎn)造成嚴(yán)重風(fēng)險。（剩余9038字）