基于图像特征衍生的水稻氮素精准监测研究OA

[Objective]To rapidly and accurately monitor the nitrogen nutrition status of rice and determine the optimal nitrogen application rate for high yield and quality.[Methods]Field experiments were conducted over two years(2022-2023)using two locally dominant rice varieties:the conventional early indica rice'zhongjiazao17'and the hybrid rice'changliangyou173'.Four nitrogen fertilizer levels(0,75,150,225 kg·hm-2,denoted as N0,N1,N2,and N3,respectively)were established.Digital camera(Canon EOS 100D,resolution 72 pixels per inch)was used to acquire rice canopy images and corresponding nitrogen nutrition data.Nitrogen nutrition monitoring models were constructed based on image features and their derived parameters.[Results]The percentage of rice pixels(PRP)in the image and its derived features showed high correlations with leaf area index(LAI),above ground biomass(AGB),and nutrition accumulation(PNA),with the best model prediction performance observed at the jointing stage.Further analysis revealed that polynominal functions based solely on RPR could effectively predict LAI,AGB,and PNA,with coefficients of determination(R2)of 0.76,0.74,and 0.79,respectively(P＜0.01),and the root mean square error(RMSE)for the model validation was 0.32 g·m-2,22.30 g·m-2,and 2.54 g·m-2,and the relative root mean square error(RRMSE)was 8.25%,7.61%,and 26.49%,respectively.In contrast,high-order exponential function derived from PRP provided superior predictions for LAI,AGB,and PNA,with R2 of 0.89,0.92,and 0.93,respectively(P＜0.01),RMSE values of 0.16 g·m-2,3.71 g·m-2,0.57 g·m-2,and RRMSE values of 4.20%,1.27%,and 5.98%(all＜10%),indicating excellent model stability.[Conclusion]Overall,the feature derivation strategy effectively improves the prediction accuracy and stability of the models,demonstrating significant application values for monitoring rice nitrogen nutrition.