基于马铃薯叶片光纤光谱信息的晚疫病患病程度预测

Prediction of the Degree of Late Blight Disease Based on Optical Fiber Spectral Information of Potato Leaves

针对马铃薯晚疫病害的早期检测和防治问题,利用光谱技术对马铃薯晚疫病叶片过氧化物酶(POD)活性进行预测,并基于POD酶活性实现了马铃薯晚疫病的患病程度预测。采集和测定处于不同温湿度及接菌时间的马铃薯叶片样本的光谱反射率和POD酶活性,选用中心化(MC)预处理方法以消除原始光谱数据的误差。为降低模型复杂程度,利用随机青蛙算法(RF)、连续投影算法(SPA)、竞争自适应加权算法(CARS)对波长进行筛选,结果表明利用CARS算法提取的72个特征波长数据建立的POD酶活性的偏最小二乘回归(PLSR)预测模型效果最好,其预测集的决定系数R^(2)_(p)为0.9581、均方根误差RMSE_(p)为25.6986 U·(g·min)^(-1)。最后利用径向基函数神经网络(RBFN N)拟合了POD酶活性和温湿度、接菌时间的关系,建立了POD酶活性的动力学模型,实现了基于POD酶活性的马铃薯晚疫病患病程度预测。结果证明利用光谱技术快速测定POD酶活性以实现马铃薯晚疫病患病程度预测是可行的。

To detect and prevent potato late disease,the p eroxidase(POD)activity of potato late-blight leaves was predicted by spectros copic techniques,and the prediction of potato late-blight disease was realized based on POD enzyme activity.The spectral reflectivity and POD enzyme activity of potato leaf samples in different temperature,humidity and inoculation time conditions were collected and measured.And the Mean Centering method is ultimat ely chosen,which is used to eliminate the error of the original spectral data.In order to reduce the complexity of the model,RF,SPA and CARS algorithms were used to filter the wavelengths,and the results showed that the partial least-square regression(PLSR)prediction model was established by using the spectral data at 72 characteristic wavelengths which are extracted by the CARS algorithm was the best.The coefficient of determination R^(2)_(p)of the prediction set is 0.9581,and the root means square error RMSE_(p)is 25.6986 U·(g·min)^(-1).Finally,the RBF radial basis network was used to fit the relationship b etween POD enzyme activity,temperature,humidity and inoculation time and estab lished a kinetic model of POD enzyme activity.So the prediction of the disease period of potato late blight based on POD enzyme activity was further realized.The results proved the feasibility of using spectroscopy to rapidly determine POD enzyme activity to predict potato late blight.