基于RGB与高光谱图像的小麦低温胁迫评估模型  

Assessment model for low temperature stress in wheat based on RGB and hyperspectral images

作　　者：余德炤 江晓东[1] 杨莹颖 张建取 忻乐 张艳 秦思容 杨再强[1] YU De-zhao;JIANG Xiao-dong;YANG Ying-ying;ZHANG Jian-qu;XIN Le;ZHANG Yan;QIN Si-rong;YANG Zai-qiang(School of Ecology and Applied Meteorology,Nanjing University of Information Science&Technology/Jiangsu Provincial University Key laboratory of Agricultural and Ecological Meteorology,Nanjing,Jiangsu 210044,China;School of Atmospheric Sciences,Nanjing University of Information Science&Technology,Nanjing,Jiangsu 210044,China)

机构地区：[1]南京信息工程大学生态与应用气象学院/农业与生态气象江苏省高校重点实验室,江苏南京210044 [2]南京信息工程大学大气科学学院,江苏南京210044

出　　处：《南方农业学报》2025年第1期97-110,共14页Journal of Southern Agriculture

基　　金：国家重点研发计划项目(2022YFD2300202)。

摘　　要：【目的】探究低温胁迫对小麦叶片叶绿素荧光参数、RGB图像参数和高光谱指数的影响,建立小麦低温胁迫评估模型,为小麦生产防灾减灾提供参考。【方法】以济麦22为研究对象,在小麦拔节期开展低温胁迫控制试验,设白天(8:00—20:00)/夜间(20:00—次日8:00)平均温度分别为8℃/0℃(T1)、6℃/-2℃(T2)和4℃/-4℃(T3)3个处理,持续时间3 d,以大田自然环境的盆栽小麦(23℃/8℃)为对照(CK),研究低温胁迫处理结束后1、3和6 d小麦叶片叶绿素荧光参数、RGB图像参数及高光谱指数的变化规律;使用一元线性回归、随机森林(RF)和人工神经网络(ANN)建立小麦低温胁迫评估模型。【结果】叶绿素荧光参数DIo/RC可作为评估小麦低温胁迫的指标。在一元线性回归模型中,使用增强型植被指数(EVI)建立的一元线性回归模型效果最佳,回归方程为y=-1.261x+1.401,决定系数(R^(2))、均方根误差(RMSE)、平均绝对误差(MAE)、平均相对误差(MRE)分别为0.536、0.058、0.045和11.31%。在RF和ANN模型中,基于RGB图像参数建立的模型精度高于基于高光谱指数建立的模型,RF模型测试集R^(2)、RMSE、MAE、MRE分别为0.771、0.042、0.033、8.57%,R^(2)相比一元线性回归模型提高43.78%,RMSE、MAE、MRE分别降低28.31%、28.06%、24.21%;ANN模型测试集R^(2)、RMSE、MAE、MRE分别为0.742、0.046、0.037、9.01%,测试集R^(2)相比一元线性回归模型提高38.34%,RMSE、MAE、MRE分别降低20.33%、18.06%、20.32%。【结论】基于RGB图像参数的RF模型效果最好、精度最高,可用于小麦的低温胁迫评估。【Objective】This study investigated the effects of low temperature stress on chlorophyll fluorescence parameters,RGB image parameters and hyperspectral indexes of wheat leaves.It aimed to establish an assessment model for wheat under low temperature stress,providing reference for disaster prevention and mitigation in wheat production.【Method】Using winter wheat variety Jimai 22 as the research material,a controlled low temperature stress experiment was conducted during the jointing stage.Three treatments were applied:daytime(8:00–20:00)/nighttime(20:00–8:00 on next day)mean temperatures of 8℃/0℃(T1),6℃/-2℃(T2)and 4℃/-4℃(T3),each lasting for three days.Potted wheat grown under natural field conditions(23℃/8℃)served as the control(CK).The changes in chlorophyll fluorescence parameters,RGB image parameters,and hyperspectral indexes of wheat leaves were analyzed on 1,3 and 6 d after the low temperature stress treatments.Wheat low temperature stress assessment models were developed using univariate linear regression,random forest(RF)and artificial neural networks(ANN).【Result】The chlorophyll fluorescence parameter DIo/RC was identified as an effective indicator for assessing wheat low temperature stress.In the univariate linear regression model,the model using the enhanced vegetation index(EVI)performed the best,with a regression equation of y=-1.261x+1.401,yielding a coefficient of determination(R^(2)),root mean square error(RMSE),mean absolute error(MAE)and mean relative error(MRE)of 0.536,0.058,0.045,and 11.31%respectively.For RF and ANN models,models based on RGB image parameters outperformed those based on hyperspectral indexes.The RF model achieved R^(2),RMSE,MAE and MRE values of 0.771,0.042,0.033 and 8.57%in the test set,with an R^(2) improvement of 43.78%and reductions in RMSE,MAE and MRE by 28.31%,28.06%and 24.21%respectively compared to the univariate linear regression model.The ANN model achieved R^(2),RMSE,MAE and MRE values of 0.742,0.046,0.037 and 9.01%,with R^(2) improving

关 键 词：小麦 叶绿素荧光参数 RGB图像 高光谱图像 低温胁迫评估模型 

分 类 号：S512.1[农业科学—作物学]