Many nations depend heavily on agriculture, thus it is essential to forecast yields in order to ensure food security. One technique for predicting a production involves integrating remote sensing data. Worldwide agricultural areas have been the subject of investigation for many years. The current study's findings demonstrate that estimation outcomes differ depending on the training's chronological context and agricultural regions. Remote sensing has greatly facilitated the identification of spatial patterns and vegetation through the use of the Normalized Difference Vegetative Index (NDVI). The XGBoost algorithm is used in this Atmospherically Resistant Vegetation Index (ARVI), Normalized Difference Moisture Index (NDMI), Normalized Difference Water Index (NDWI), temperature, precipitation, and others, to predict the yield of crops. According to the study's findings, the XGBoost algorithm's crop yield prediction has a coefficient of variance with an RMSE of 1.60.