基于Stacking集成算法的中國南方地區(qū)糧食產(chǎn)量預(yù)測

打開文本圖片集

關(guān)鍵詞：Stacking集成算法；糧食產(chǎn)量；中國南方；預(yù)測

中圖分類號：F326.11；S126 文獻(xiàn)標(biāo)識碼：A

文章編號：0439-8114（2025）05-0155-05

DOI：10.14088/j.cnki.issn0439-8114.2025.05.024 開放科學(xué)（資源服務(wù)）標(biāo)識碼（OSID）：

Grain yield prediction in southern China based on Stacking ensemble algorithm

MADian-jing'，ZHAO Jia-song1，YAN Wei-yu1，DUANGuang-jun1，LIU Zhen-yang2，WU Shao-tian’ （1.School of Big Data，Yunnan Agricultural University，Kunming 65O2O1，China; 2.School of Data Science and Engineering，Kunming City College，Kunming 65Oo32，China）

Abstract：Basedonthe grainyielddataand11-dimensionalrelevantactorsfromAnhui，Hubei，Hunan，Jiangsu，andSichuanprov inces insoutherChinabetwen1998and2O22，theBP-SVR-Stacking grainyieldpredictionmodelbasedonthe Stacking ensemble algorithmwasdevelopedandcomparativelyanalyzedwiththeBPneuralnetwork modelandSVRmodel.Theresultsindicatedthatthe mean absolute error （ MAE ）and mean absolute percentage error （ MAPE ）of the BP-SVR-Stacking model were significantly lower than thoseof theBPneuralnetworkmodelandSVRmodel，hichdemonstratedthesuperiorpredictioncapabilityoftheBP-SVR-tacking modeloversingle machinelearningmodels.ComparedwiththeBPneuralnetworkmodelandSRmodel，thecoeficientofdetermination （ R2 ）of the BP-SVR-Stacking modelincreasedby0.124and0.122 respectively，suggesting thatthe BP-SVR-Stacking model possessed excellent fiting capability and prediction performance.

Key Words：Stacking ensemble algorithm；grain yield；southern China;prediction

糧食產(chǎn)量是一個涉及生態(tài)學(xué)、社會學(xué)、經(jīng)濟(jì)學(xué)和統(tǒng)計學(xué)的復(fù)雜問題，其產(chǎn)量受環(huán)境、科技、經(jīng)濟(jì)、政策和勞動力等多重因素的影響[1。（剩余7955字）