KLASIFIKASI KANDUNGAN NITROGEN PERTANIAN TANAMAN PADI MENGGUNAKAN MODIS SINTETIK

Abstract

Remote sensing is the science that has an important role in obtaining information on the object under study without having to make direct contact with the object. Remote sensing is a solution to a good farm system as it can provide precise information and good analysis. This study was conducted based on the application of remote sensing science in order to classify the nitrogen content of rice farming. Nitrogen has such an important role in the growth of rice plants. The objective in this research is to predict the classification about the nitrogen content in a rice farming areas, especially in Karawang, West Java.

Classification process is done in two phases, training and testing. The method used for the training phase is kurtosis projections and Jackknife procedure. The results of the training phase is to get the mean and standard deviation to be used for testing. In the testing phase classification process is carried out based on MODIS imagery for the area Karawang, West Java.

The experiment results is known that on March 30, 2012 approximately 44% of the total area of rice farming in Karawang (107.525 ha) which contains enough nitrogen, while the other has 56% less nitrogen content. The evaluation shows the percentage accuracy of the method in classifying the data is about 71%.

Key words

Jackknife Procedure, Kurtosis Projection, Mahalanobis Distance, MODIS, Nitrogen, Remote Sensing