Paper Title

Abstract - Oil palm (Elaeis guineensis Jacq.) trees are one of the most important agriculture sector and economic development in Thailand. However oil palm trees are damaged and lose by diseases that can decrease the profitability of the business. Currently, remote sensing technology uses to investigate for detecting and mapping for agriculture section. This study aims to use Sentinel-2 satellite image and ground observation data to identify the characteristics of oil palm trees based on three sites of healthy oil palm tree area, diseases oil palm tree area and mixed oil palm tree area. For this purpose, 8 vegetation indices of Green Normalized Difference Vegetation Index (GNDVI), Normalized Difference Vegetation Index (NDVI), The Normalized Difference Index (NDI45), The Ratio Vegetation Index (RVI), The Modified Soil Adjusted Vegetation Index (MSAVI) and The Meris Terrestrial Chlorophyll Index (MTCI) were used as a substitute to plant biomass and indicator of oil palm tree disturbance. Linear regression model was applied to each of the derived VIs to determine the index with the strongest relationship to the measured three oil palm areas. The outcome of this study showed (1) the most effective indicators were NDVI in heathy oil palm area and RVI index in diseased oil palm area (R2 = 0.48 and 0.68 respectively). (3) MSAVI performed best in capturing various trend patterns related to the greenness of vegetation in mixed oil palm tree area (R2 = 0.44). Moreover, the results show that the overall Support Vector Machine (SVM) classification accuracy is 72.97%, the Kappa coefficient 0.56 in healthy oil palm area, 64.16% and 0.40 in diseased oil palm area and 50.00% and 0.37 in mixed oil palm area. Comparing to UAV SVM classification, it found that overall accuracy values were higher than Sentinel-2 SVM classification. This work recommends an innovative methodology and very high spatial and spectral resolutions for quantitative and qualitative analysis of spatial distribution of symptomatic oil palm trees. Keywords - Sentinel-2; Oil Palm; Disease; Vegetation Indices; Maximum Likelihood Classification.