Assessing Durum Wheat Yield through Sentinel-2 Imagery: A Machine Learning Approach
Maria Bebie, Chris Cavalaris, Aris Kyparissis
Abstract
Two modeling approaches for the estimation of durum wheat yield based on Sentinel-2 data are presented for 66 fields across three growing periods. In the first approach, a previously developed multiple linear regression model (VI-MLR) based on vegetation indices (EVI, NMDI) was used. In the second approach, the reflectance data of all Sentinel-2 bands for several dates during the growth periods were used as input parameters in three machine learning model algorithms, i.e., random forest (RF), k-nearest neighbors (KNN), and boosting regressions (BR). Modeling results were examined against yield data collected by a combine harvester equipped with a yield mapping system. VI-MLR showed a moderate performance with R2 = 0.532 and RMSE = 847 kg ha−1. All machine learning approaches enhanced model accuracy when all images during the growing periods were used, especially RF and KNN (R2 > 0.91, RMSE < 360 kg ha−1). Additionally, RF and KNN accuracy remained high (R2 > 0.87, RMSE < 455 kg ha−1) when images from the start of the growing period until March, i.e., three months before harvest, were used, indicating the high suitability of machine learning on Sentinel-2 data for early yield prediction of durum wheat, information considered essential for precision agriculture applications.