An Optimal Approach for Land-Use\u2009/\u2009Land-Cover Mapping by Integration and Fusion of Multispectral Landsat OLI Images: Case Study in Baghdad, Iraq

Hayder Dibs,Jawad K Al-Rifaie,Hashim Ali Hasab,Nadhir Al-Ansari

doi:10.1007/s11270-020-04846-x

Abstract

Using solely an optical remotely sensed dataset to obtain an accurate thematic map of land use and land cover (LU/LC) is a serious challenge. The dataset fusion of multispectral and panchromatic images play a big role and provide an accurate estimation of LU/LC map simply because using a dataset from different spectrum portions with different spatial and spectral characteristics will improve image classification. For this study, the Landsat operational land imager multispectral and panchromatic images were adopted. This study aimed to investigate the effectiveness of using a panchromatic highly spatial resolution to refine the methodology for LU/LC mapping in Baghdad city, Iraq, by performing a comparison of classifications using different algorithms on multispectral and fused images. Different classification algorithms were employed to classify the data set; minimum distance (MD) and the maximum likelihood classifier (MLC). A suitable classification method was proposed to map LU/LC based on the outcome results. The result evaluation was conducted by applying a confusion matrix. An overall accuracy of a fused image using a principal component-based spectral sharpening algorithm and classified by the MLC classifier reveals the highest accurate results with an overall accuracy and kappa coefficient of 98.90% and 0.98, respectively. Results showed that the best methodology for LU/LC mapping of the study area is found from fusion of multispectral with panchromatic images via principal component-based spectral algorithm with MLC approach for classification.

Highlights

Reliable and accurate land use and land cover (LU/LC) classification is important for applications in a wide488 Page 2 of 15 range (Zhang 2010)
The results reveal that the classification accuracy obtained from applying the maximum likelihood classifier (MLC) classifier is the highest accuracy when applied on the fused image between MS and PAN; the overall accuracy was about 98.90% with a kappa coefficient of about 0.98
The research aims to find out the improving methodology for LU/LC mapping Baghdad city by conducting classification comparisons using different approach (PC and CN) methods on MS and fused images

Summary

Introduction

488 Page 2 of 15 range (Zhang 2010) Examples of these classification approaches that have been employed in various disciplines and applications include the following: global change monitoring, land use detection, geographical information data updating, natural hazards modeling, and urban expansion prediction (Cihlar and Jansen 2001; Lu et al 2011; Sang et al 2014; Hayder 2015; Otukei et al 2015). Remote sensing (RS) is useful for determining LU/LC estimation using suitable datasets and classification techniques. Selection of a suitable classifier approach is critical for obtaining an accurate LU/LC thematic map. Researchers and analysts have faced difficulties and challenges in terms of selecting which classification algorithm to use (Srivastava et al 2012; Chasmer et al 2014; Anjan and Arun 2019)

Objectives

Methods

Results

Conclusion