Normalized Sunlit Shaded Index (NSSI) for characterizing the moisture stress in wheat crop using classified thermal and visible images

In this study, we used proximal thermal and visible imaging system to separate four different components of the wheat crop, i.e., canopy and soil under sunlit and shaded conditions using Support Vector Machine method of supervised image classification approach under different moisture stress treatments. A Normalized Sunlit Shaded Index (NSSI) was developed to characterize the status of the wheat crop grown under moisture stress conditions at different growth stages. Results demonstrated that Thermal image-based NSSI (TI-NSSI) had the best correlations with all the measured crop biophysical parameters than the visible image (VI-NSSI). However, the r(2) decreased with an increase in moisture stress. Among the different biophysical parameters tested in this study, TI-NSSI showed the highest significant negative correlation (- 0.962***) with Radiation use efficiency (RUE). In general, irrespective of the moisture stress VI-NSSI gave the least relationship with all the biophysical parameters tested. Further regression analysis showed that TI-NSSI could explain the variations in RUE under different moisture stress conditions with R-2 > 0.960. Regression analysis with yield showed that TI-NSSI under peak vegetative growth stage (83 DAS) adequately captured the variations in crop yield under moisture stress conditions.