利用约束随机森林和贝叶斯优化算法的小麦条锈病遥感监测  

Remote Sensing Monitoring of Wheat Stripe Rust Using Constrained Random Forest and Bayesian Optimization Algorithm

作　　者：薛一阳 竞霞[1] 叶启星 杜凯奇 李冰玉 XUE Yiyang;JING Xia;YE Qixing;Du Kaiqi;Li Bingyu(College of Geomatics,Xi’an University of Science and Technology,Xi’an 710054,China)

机构地区：[1]西安科技大学测绘科学与技术学院,陕西西安710054

出　　处：《遥感技术与应用》2025年第1期69-76,共8页Remote Sensing Technology and Application

基　　金：国家自然科学基金项目(42171394、41961052)。

摘　　要：为了改善小样本数据的过拟合问题,提高小麦条锈病遥感监测模型的泛化能力和预测精度,以2018年河北省中国农业科学院实验站获取的冠层日光诱导叶绿素荧光(Solar-Induced Chlorophyll Fluorescence,SIF)为数据源,利用代价复杂性剪枝(Cost-Complexity Pruning,CCP)算法对随机森林回归(Random Forest Regression,RFR)方法进行剪枝约束,并结合贝叶斯优化(Bayesian Optimiazation,BO)算法对随机森林回归进行超参数选取,构建了基于约束随机森林回归(Constrained Random Forest,CO-RFR)算法小麦条锈病严重度预测模型,并将其与分类回归树(Classification And Regression Tree,CART)算法、传统RFR算法以及多元线性回归(Multiple Linear Regression,MLR)方法构建的小麦条锈病遥感监测模型精度进行比较。结果表明:①CORFR模型的估测精度最高,更适合于小样本数据下的小麦条锈病遥感监测。其中,在验证数据集中CO-RFR模型预测病情严重度(Severity Level,SL)和实测SL间的平均RMSE比RFR、CART和MLR模型分别减少了43%、50%和40%,平均R^(2)分别提高了56%、47%和40%。②增加约束条件能够有效改善模型的过拟合现象,提高模型的泛化能力。其中,RFR模型训练集预测SL值和实测SL值间的平均RMSE较验证集减少了62%,表明模型训练集精度远高于验证集,模型出现过拟合,而CO-RFR模型训练集预测SL值和实测SL值间的平均RMSE较验证集减少了8%,表明模型拟合效果较好,过拟合现象得到明显改善。该研究对提高小样本数据下的小麦条锈病病情严重度的遥感预测精度具有重要意义,同时亦为其它作物的胁迫监测提供了应用参考。In order to improve the overfitting problem of small sample data and improve the generalization ability and prediction accuracy of the wheat stripe rust remote sensing monitoring model,this paper uses the Solar In⁃duced Chlorophyll Fluorescence(SIF)in the canopy obtained by the Chinese Academy of Agricultural Sciences Experimental Station in 2018 as the data source,The Cost Complexity Pruning(CCP)algorithm is used to prune the Random Forest Regression(RFR)method,and the Bayesian Optimization(BO)algorithm is used to select hyperparameter for random forest regression,and a prediction model of wheat stripe rust severity based on the constrained random forest regression(CO-RFR)algorithm is Constructed,And compare the accuracy of the remote sensing monitoring model for wheat stripe rust with the Classification And Regression Tree(CART)algorithm,traditional RFR algorithm,and Multiple Linear Regression(MLR)method.The results indicate that:(1)The CO-RFR model has the highest estimation accuracy and is more suitable for monitoring the severity of wheat stripe rust under small sample data.Among them,in the validation dataset,the average RMSE between the Severity Level(SL)predicted by the CO-RFR model and the measured SL was reduced by 43%,50%,and 40%,respectively,compared to the RFR,CART,and MLR models,and the average R^(2) was increased by 56%,47%,and 40%,respectively.(2)Adding constraints can effectively improve the over⁃fitting phenomenon of the model and enhance its generalization ability.Among them,the average RMSE be⁃tween the predicted SL value and the measured SL value in the RFR model training set decreased by 62%com⁃pared to the validation set,indicating that the accuracy of the model training set was much higher than that of the validation set,and the model showed overfitting.However,the average RMSE between the predicted SL value and the measured SL value in the CO-RFR model training set decreased by 8%compared to the valida⁃tion set,indicating that the model fitting effect was good and the overfittin

关 键 词：过拟合 约束随机森林 贝叶斯优化 日光诱导叶绿素荧光 小麦条锈病 模型精度 

分 类 号：S435.121.452[农业科学—农业昆虫与害虫防治] S127[农业科学—植物保护]