Multispectral Image Classification Based on the Bat Algorithm

Abstract

There are many traditional classification algorithms used to classify multispectral images, especially those used in remote sensing. But the challenges of using these algorithms for multispectral image classification are that they are slow to implement and have poor classification accuracy. With the development of technologies that mimic nature, many researchers have resorted to using intelligent algorithms instead of traditional algorithms because of their great importance, especially when dealing with large amounts of data. The bat algorithm (BA) is one of the most important of these algorithms. This study aims to verify the possibility of using the BA to classify the multispectral images captured by the Landsat-5 TM satellite image of the study area. The study area represents the Mosul area located in the Nineveh Governorate in northwestern Iraq. The purpose is not only to study the ability of the BA to classify multispectral images but also to obtain a land cover map of this region. The BA showed efficiency in the classification results compared to Maximum Likelihood (ML), where the overall accuracy of classification when using the BA reached (82.136%), while MLreached (79.64%).