Table 3 The prediction accuracy of normalized thermal infrared indices

From: Monitoring of drought stress and transpiration rate using proximal thermal and hyperspectral imaging in an indoor automated plant phenotyping platform

Index	RMSE	R²	MAPE (%)
CTD_in	0.66	0.32	55
CTD_out	0.66	0.44	44
CTD_gz	0.8	0.02	62
CSI_in	0.8	0.01	61
CSI_out	0.73	0.02	62
CSI_gz	0.79	0.02	60
ICWSI_in	0.78	0.05	58
ICWSI_out	0.86	0.02	61
ICWSI_gz	0.8	0.05	57
CWSI_in	0.76	0.1	61
CWSI_out	0.77	0.13	60
CWSI_gz	0.85	0.03	62
CWSI_{Ta_in}	0.8	0.11	62
CWSI_{Ta_out}	0.68	0.39	51
CWSI_{Ta_gz}	0.79	0.06	65
T_dry-T_p	0.61	0.41	50
T_BS-T_p	0.8	0.04	57
TRI_in	0.72	0.17	60
TRI_out	0.7	0.21	54
TRI_gz	0.76	0.03	61

Index-based models were created for each index and the prediction accuracy was evaluated by calculating the median test RMSE, R² and MAPE of 100 bootstrap samples

Back to article page

ISSN: 1746-4811

Contact us

Submission enquiries: journalsubmissions@springernature.com