Assessing Land Use/Land Cover Change Using Multitemporal Landsat Data in Agadir City (Morocco)

The aim of this study is to highlight Land Use/Land Cover (LULC) sever changes dynamics in Agadir city of Morocco during the period 1986–2019. For this purpose, Landsat imageries (5 TM, 7 ETM+, and 8 OLI) acquired in 1986, 1996, 2003, 2014, and 2019 years, were classified using Support Vector Machine (SVM) algorithm to produce LULC maps. First, spectral indices such as the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Built-up (NDBI) were used to discriminate the four LULC classes (built-up areas, bare lands, vegetation, and water bodies) of the study area. Moreover, change detection was applied on classified maps to characterize LULC dynamics class by class. The results reveal a spatial expansion over the 33 years, with high overall accuracy and kappa coefficient values. In detail, vegetation and bare lands have been decreased by 95.58% and 72.06%, respectively, while the built-up areas have been increased by an amount of 66.86%. Overall, the findings of this study could assist planners and decision-makers to guide, in a good manner, the sustainable land development of the city.