基于XGB-KF模型的農(nóng)業(yè)溫室溫度預測

打開文本圖片集
doi:10.11835/j.issn.1000-582X.2025.04.009
引用格式:黃威,賈若然,鐘坤華,等.基于XGB-KF模型的農(nóng)業(yè)溫室溫度預測[J].重慶大學學報,2025,48(4): 108-114.
中圖分類號:TP399 文獻標志碼:A 文章編號:1000-582X(2025)04-108-07
Agricultural greenhouse temperature prediction based on the XGB-KFmodel
HUANG Wei'2, JIA Ruoran, ZHONG Kunhua', LIU Shuguang'2 (1.Chogqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing 400714, P.R.China; 2. University of Chinese Academy of Sciences,Beijing 10o049, P.R.China; 3.Iflytek Co., Ltd., Hefei 230031, P.R. China)
Abstract:To addess the challenge of agricultural greenhouse temperature measurement being highly susceptible to noise,which limits direct prediction accuracy, this study proposes an integrated prediction model, XGB-KF, combining XGBoost and the Kalman filter.First, the model estimates the current greenhouse temperature using XGBoost.Then,the Kalman filter dynamicall adjusts the estimated result to refine the prediction.Numerical experiments are conducted using sensor data from a greenhouse in Zhuozhou, with root mean square error (RMSE) as the main evaluation metric. Compared with XGBoost, Bi-LSTM, and Bi-LSTM-KF methods, the XGB-KF model reduces RMSE by 5.22% , 10.85% and 7.45% respectively.
Keywords: integrated model; machine learning; time series; greenhouse temperature
溫度作為農(nóng)作物生長的重要環(huán)境因素,影響著作物的生長速度、產(chǎn)量和質(zhì)量,如何準確預測和調(diào)控溫度成為現(xiàn)代農(nóng)業(yè)的重要問題。(剩余8282字)