Inversion of SPAD Values of Rice Canopy Based on Aerial Images Taken by Unmanned Aerial Vehicle
To realize the high-throughput detection of chlorophyll content of rice using aerial images taken by unmanned aerial vehicle(UAV),Zhaoyou 5431,a three-line indica hybrid rice variety,was used as the materials,three planting density levels and five nitrogen application levels were set,and a total of 15 treatments were performed.The aerial images were obtained by Dajiang Genie 4RTK UAV and the SPAD value of rice leaves was manually measured at different growth stages of rice.Seven kinds of visible light vegetation index that were significantly correlated with the SPAD value of rice leaves were selected,and the inversion model of SPAD value of rice leaves was constructed by linear regression and machine learning methods.The optimal prediction model of SPAD value of rice leaves was determined by accuracy verification.The results showed that among the machine learning models,the accuracy of random forest model was higher than that of other regression models,and the model constructed by this algorithm had higher prediction accuracy.The model indicators were modeling set R2 of 0.85 and RMSE of 2.73,validation set R2 of 0.76 and RMSE of 3.64.Therefore,the machine learning model can provide reference for non-destructive and rapid monitoring of rice leaf SPAD value.
NETL
NSTL
万方数据
