Spectral vegetation indices and their relationships with nitrogen stress levels

This thesis describes the development of statistical models to determine the relationships between vegetation indices and bush bean plant nitrogen stress levels thereby help early detection of bush bean nutritional stress. Two approaches, statistical analysis by SAS procedure and genetic algorithm (GA) were employed. Polynomial regression was used to fit data under all possible two-bands combinations. The best bands identified were 700nm, 710 nm, 720 nm, and 750 nm. The best model selected by both SAS and GA was second degree polynomial for RVI with an adjusted R2 value of 0.9144. Comparison of these two approaches showed that SAS procedure could provide accurate result but was less efficient. GA integrated both statistical analysis and model selection and was more efficient.