FT-IR absorbance data for early detection of oil palm fungal disease infestation

Basal stem rot (BSR) is a serious fungal disease in oil palm plantations which potentially could reduce the market share of palm oil for Malaysia. Due to the preventing great losses in production and reducing the use of chemicals, early detection of Ganoderma fungal infection is critical for management of this disease. At present study, we propose to apply a mid-infrared spectroscopy technique for detection of infected oil palm trees at three stages of infection. Leaf samples of healthy, mild, moderate and sever-infected trees were measured using Fourier transform infrared (FTIR) spectrometers system to obtain absorbance data from the range of 2.55-25.05 μm. Single bounce ATR accessory with and without dilution with potassium bromide (KBr) were used in this study. Savitsky-Golay method was used for smoothing. The selected principal component (PC) scores were used as input features in quadratic discriminant analysis (QDA) as a pattern recognition algorithm. The results indicated that QDA-based algorithm can distinguish between healthy and infected leaves at three stages of infection with high classification accuracies (>80%) when leaves demonstrated that the proposed technique has the potential for early detection of the Ganoderma disease