Assessing the Accuracy of Land Use Classification Using Multi-spectral Camera From LAPAN-A3, Landsat-8 and Sentinel-2 Satellite: A Case Study in Probolinggo-East Java

Abstract

The LAPAN-A3 is the third microsatellite generation developed by the Research Center for Satellite Technology. The satellite can be used for land classification, agriculture monitoring, drought monitoring, and land use change. This study aims to classify land use and land cover in the research area. The main image used is LAPAN-A3; the compared images are Landsat-8 and Sentinel-2. Three images were taken on the same day and selected on cloud-free terms. The classification process starts with determining the region of interest (ROI) and the class. The classification is divided into six classes: water, forests, rice fields, settlements, open land, and coastal areas. The classification technique uses supervised learning with the maximum likelihood method. This study used Landsat 8 and Sentinel-2 data to compare the results obtained from LAPAN-A3. The accuracy test results for the LAPAN-A3 and Landsat-8 are 84.7042% and 0.783, respectively. While the accuracy test of LAPAN-A3 and Sentinel-2 is 72.2313%, the kappa value is 0.6394. The classification of two comparisons is quite accurate, with an accuracy of more than 70%. The LA3 classification successfully identifies water and coastal areas. The producer and accuracy is substantiated by comparing the results with both Landsat-8 and Sentinel-2 satellite data, which exhibit an accuracy rate exceeding 85%. Finally, LAPAN-A3 has great potential for classifying land use and land cover when compared to Landsat 8 and Sentinel-2 images, but future research should increase the number of datasets and vary the research area to improve the results.