An Extensive Study on Satellite Images of Sentinel 2 for Crop Type Identification

India is primarily based on agriculture because of its massive rural population. Although controlled trials and historical data can provide rough estimates of crop production, their accuracy is low. Estimates of the agricultural yield may be subject to more than one type of bias. Recent advances in learning have enabled the efficient extraction of agricultural production statistics from remote sensing photos depending on the crop in the field, thereby assisting policymakers in the development of more effective policies and administration. To estimate crop yields, one can apply AI techniques such as deep learning or machine learning to remotely sensed images of crops of interest, classifying the images into dataset and image quality. In this study, we investigate how physical factors including soil, climate, and vegetation indices affect crop yields. The satellite data gathered from a distinct study site in the central portion of India is put through a series of statistical tests, including correlation and multiple regression analysis, to identify the parameters most likely to accurately predict crop yield. We also look into what influences satellite photos and discuss what it means for the future.