Investigating Sentinel-1 and Sentinel-2 Data Efficiency in Studying the Temporal Behavior of Wheat Phenological Stages Using Google Earth Engine

Crop monitoring is critical for sustaining agriculture, preserving natural resources, and dealing with the effects of population growth climate change. The Sentinel missions, Sentinel-1 Sentinel-2, provide open imagery at a high spatial temporal resolution. This research aimed (1) to evaluate profiles derived from Sentinel-2 time series data in deducing dates phenological stages wheat germination fully mature plant using Google Earth Engine (GEE) JavaScript interface (2) assess relationship between optical/ SAR remote sensing indices developing an accurate phenology estimation model extrapolate it regional scale. Firstly, were evaluated terms wheat. Secondly, used their linear regression (LR) technique. Thirdly, best performing optical radar selected stage prediction. Fourthly, distribution TIP region was mapped by Random Forest (RF) classification fusion 2 images, overall accuracy 95.02%. These results characterize on scale Temporal Normalized Phenology Index (TNPI) predicted models. obtained revealed that dense allowed germination, tillering, jointing heading, maturity, harvesting be determined support crop calendar. TNPIincrease TNPIdecrease declining part NDVI profile NDVIMax, NDVIMin2 higher TNPI values (from 0.58 1) than rising 0.08 0.58). (3) most models predicting generated WDVI VH–VV indices, having R2 equal 0.70 0.84 heading maturity.