Dynamic monitoring of biomass of rice under different nitrogen treatments using a lightweight UAV with dual image-frame snapshot cameras

Table 2 Estimated aboveground biomass (AGB) and panicle biomass (PB) in rice by random forest (RF) method

Camera type	Features	Estimation	AGB	PB
RGB	VDVI, NGRDI, VARI, GRRI, VEG, MGRVI, Hcsm	r²	0.85	0.48
		RMSEP	0.23	0.13
		RRMSE	15.57%	16.93%
Multispectral	NDSI, SR, MNDSI	r²	0.83	0.53
		RMSEP	0.25	0.12
		RRMSE	17.02%	14.91%
RGB + multispectral	VDVI, NGRDI, VARI, GRRI, VEG, MGRVI, NDSI, SR, MNDSI, Hcsm	r²	0.90	0.64
		RMSEP	0.21	0.11
		RRMSE	14.05%	13.74%

The r², RMSEP and RRMSE represent the coefficient of determination, the prediction of root mean square error and relative RMSE, respectively

ISSN: 1746-4811