Application of Remote Sensing and GIS for the Quantification of Spatiotemporal Changes—Land Use/Land Cover in Steppe Landscapes: Case of the Djelfa Region (Algeria)

The detection of changes in landscape dynamics relies heavily on the effective integration of modern technologies and conventional ecological monitoring techniques, especially remote sensing and GIS, which are currently considered very important techniques for the study of LULC. This study illustrates the spatiotemporal dynamics of LULC in an Algerian steppe region affected by desertification. For this study, we relied on field data, as well as satellite images from Landsat 5 TM and Landsat 8 OLI, to perform a diachronic analysis of this steppe landscape, which is mainly composed of seven thematic classes: forest, agriculture, rangeland, wetland, built-up land, sandy land, and bare soil/rocky soil. Visual interpretation was employed as a starting point, followed by an unsupervised classification methodology using the ISODATA algorithm supported by seven different spectral indices calculated algebraically and the best composites for the identification of the characteristics of the terrain at different dates to find clusters and determine land use types. The Principal Component Analysis was also used to extract the most useful spectral information by compressing the redundant data contained in each spectral channel. Based on the results, we were able to identify the landscape units for both dates with very satisfactory results. Overall classification accuracy of 95% with a kappa coefficient of 0.94 for 1987 and 91% with a kappa coefficient of 0.90 was obtained for 2020. The analysis of the results showed that the Region of Djelfa has undergone a significant change. The results obtained revealed that the areas of forest, sandy land, and wetland have strongly decreased with rates of change of − 28.55%, − 84.65%, and − 27.27%, respectively, while that of the class of agriculture, rangeland, built-up land, and bare–rocky soil have experienced an increase with positive rates equal to 290.06%, 1.25%, 377.13, and 161.75%, respectively. These changes have been caused by the combined anthropogenic pressure as well as the extreme drought with very low PDSI equal to − 3.16 in 2020 which will help on the spread of diseases and put in difficulty the process of spontaneous regeneration of the old trees and the shrinking of the surface covered by water. Increase in population (urban and rural) and evolution of many agricultural practices in the region are also among the causes of change in LULC in the study area.