Change Detection Techniques for Land Cover Change Analysis Using Spatial Datasets: a Review

The change detection (CD) methods explore the potential of remote sensing (RS) spatial datasets in various land use/land cover (LU/LC) applications. These methods are used to analyze the LU/LC dynamics using various high and medium-resolution multi-spectral remote sensing satellite datasets (Landsat-TM/ETM+/OLI, IRS LISS-3 & 4, Sentinel-2, SPOT, and ASTER). The study’s objective is to summarize multiple changes in the last two decades in land use applications at the regional and international levels using traditional and advance change detection methods. Mapping of LU/LC dynamics at regional and global scales is essential for various land use applications (vegetation monitoring, crop cultivation monitoring, urban planning, landslide, and socio-economic dynamics). The review study showed that machine learning and deep learning techniques play an essential role in classification and change detection applications. The deep learning methods more effectively identify the changes in LU/LC (due to human activities and natural phenomena) than other traditional methods. The present study analyzes the conventional and advanced methods of change detection methods and various challenges and problems facing during the change detection.