Pansharpening involves merging a high-resolution panchromatic image with a low-resolution multispectral image to create a fused image that is more informative for remote sensing applications. Various techniques have been developed to improve fusion results by leveraging the spatial and spectral characteristics of the input images. In recent years, deep learning has significantly advanced pansharpening, offering promising results through its strong feature extraction and reconstruction capabilities. However, there is a lack of comprehensive analysis of the latest deep learning techniques across different fusion applications. This paper provides a review of various Pansharpening methods employing deep learning, comparing them based on optimal parameters. It also discusses the limitations, challenges, issues, and future directions in Pansharpening approaches.