Crop identification on specific parcels and the assessment of soil management practices are important for agro-ecological studies, greenhouse gas modeling, and agrarian policy development. Accurate crop identification can achieve a good estimation for crop sown acreage, planting structure and spatial distribution, as well as provide key input parameters for crop yield estimation model. The research in hyper spectral image (HSI) analysis is important due to its potential applications in real life. Hyper spectral imaging results in multiple bands of images that make the analysis challenging due to the increased volume of data. The spectral, as well as the spatial correlation between different bands, conveys useful information regarding the scene of interest. This research mainly focus on the role of XAI (explainable artificial intelligence) in smart agriculture by identification of crops, calculating the relative and relevant vegetation indices. The definition of relevant data sources and generation of VAR maps for the fertilization and seeding.