High throughput analysis of leaf chlorophyll content in sorghum using RGB, hyperspectral, and fluorescence imaging and sensor fusion

Table1 Test results of using the selected vegetation indices computed from different imaging data to predict chlorophyll content for sorghum plants

			Calibration dataset with fivefold validation	Calibration dataset	Validation dataset	Entire dataset
Model 1 (without DAS)	Without feature reduction	R²	0.84	0.86	0.90	0.87
		RMSE	60.70	57.53	51.34	55.39
		RPD	2.49	2.62	3.16	2.77
Model 2 (with DAS)	Without feature reduction	R²	0.87	0.88	0.92	0.89
		RMSE	54.68	51.89	45.54	49.89
		RPD	2.76	2.90	3.57	3.08
	With feature ‘Hue’ reduction	R²	0.87	0.88	0.92	0.90
		RMSE	54.60	51.61	45.37	49.64
		RPD	2.76	2.92	3.58	3.09

ISSN: 1746-4811