Hyperspectral Signal Analysis for Detecting Disease Infection in Oil Palms

Hyperspectral remote sensing has been applied to many agriculture applications such as crop stress and diseases, however, the potential use of this technique for disease detection in oil palms under field conditions is unknown. Hence, this research was conducted to investigate the applicability and feasibility of using a portable high resolution hyperspectral remote sensing instrument to identify and discern differences in spectral reflectance of oil palm leaves with and without Ganoderma infections. This study used the reflectance and first derivative spectra as input data in selecting the best bands that can discriminate between the healthy and the two levels of Ganoderma-infected oil palms. The results indicate that spectral derivative data have more bands that show significant differences between the classes than the use of reflectance data only. The preliminary results indicate that by using hyperpsectral data, it is possible to detect the presence of Ganoderma infection in oil palm but early detection is still very challenging.