Rice crop mapping using multi-temporal MODIS imagery in the northern part of west java province, Indonesia

Rice is the staple food in Indonesia. Information on rice crop growing areas is useful for relevant agencies to devise better strategies to ensure security and stability of national food. The main objective of this study is to map rice cropping patterns using Moderate resolution imaging spectroradiometer (MODIS) data in the northern part of West Java Province, Indonesia. This study area is one of the key rice producing regions in Indonesia. It consists of nine districts, covering approximately 13,155 km² (38% of the total area of the West Java province). There are two rice cropping systems in this region, namely single-cropped rain-fed rice and double-cropped irrigated rice. The data were processed for 2011. The methodology comprises four main steps: (1) data preprocessing to construct smoothed timeseries MODIS vegetation indices, including the normalized difference vegetation index (NDVI), land surface water index (LSWI), normalized difference built-up index (NDBI), and wavelet transform, (2) image masking to eliminate forest, water, vegetation, urban, height elevation, and steep slope areas to limit our analysis to rice-cropped areas, (3) rice crop classification using the supervised support vector machine (SVM) classifier, and (4) error analysis using the ground reference data and rice area statistics. The preliminary results indicated that there was a good agreement between the 2011 MODIS-derived rice area and the 2011 statistical data (R²=0.98). The spatial comparison between the rice areaderived from MODIS data in 2011 and that of the 2008 ground referencemapalso reaffirmed the overall accuracy of88.78%. Copyright