Using Sentinel-2 Data to Predict Nitrogen Uptake in Maize Crop
Alireza Sharifi
Abstract
Maize nitrogen uptake map can give growers a good opportunity in order to have valuable information regarding the efficiency of nitrogen usage in their field. The spectral information of Sentinel-2 satellite data can be used for estimating maize nitrogen uptake. In this article, Sentinel-2 data as an efficient tool were used to assess the usage of vegetation indices over three years (2017-2019), in three different locations and growing conditions to compute crop nitrogen uptake. These types of data can be used for developing an array of precision agriculture applications. Three different farms located in various climate conditions have opted for this research. For each farm, ten reference points in each year were selected to estimate a maize nitrogen uptake predictive model and use for evaluation procedure (30% of field data was for accuracy assessment and the rest of them for model prediction). At peak greenness (peak biomass) date, eight spectral vegetation indices were used for determining maize nitrogen uptake. Among these vegetation indices, simple ratio red-edge had the highest performance. It could be confirmed from the highest R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and the lowest root-mean-squared error (RMSE) values (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.91 and RMSE = 11.34 kg/ha). Implementing this model in three different sites under various conditions proved the most top performance and accuracy of it. As a result, using near-infrared and red-edge bands in vegetation indices would be the better predictor for maize nitrogen uptake.