 The paper proposes a deep learning spatiotemporal data fusion approach based on very deep super resolution, VDSR, to fuse NDVI retrievals from Sentinel-2 and Landsat-8 images, which outperforms other data fusion algorithms in generating the least blurred images and most accurate predictions of synthetic NDVI values. This algorithm has broad prospects to improve near-real-time agricultural monitoring purposes and derivation of crop status conditions in the field scale. This article was offered by Abdulaziz Tisha, Abdelgini Bouda, and Tarik Ben-Abdeluahab.