This study investigates the impact of spatial resolution enhancement on supervised classification accuracy using Landsat 9 satellite imagery, achieved through pan-sharpening techniques leveraging Sentinel-2 data. Various methods were employed to synthesize a panchromatic (PAN) band from Sentinel-2 data, including dimension reduction algorithms and weighted averages based on correlation coefficients and standard deviation. Three pan-sharpening algorithms (Gram-Schmidt, Principal Components Analysis, Nearest Neighbour Diffusion) were employed, and their efficacy was assessed using seven fidelity criteria. Classification tasks were performed utilizing Support Vector Machine and Maximum Likelihood algorithms. Results reveal that specific synthetic PAN bands, notably PAN10, PAN2, and PAN9, demonstrate superior performance in image fusion and classification tasks. This study underscores the significance of selecting fusion algorithms and panchromatic bands tailored to applications, with Support Vector Machine classifiers showcasing resilience across diverse fusion methods. Even though the PAN8 band has exhibited lower overall accuracy, it is helpful in effectively delineating some land cover classes.
