Assessing Durum Wheat Yield through Sentinel-2 Imagery: A Machine Learning Approach

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 R-2 = 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 (R-2 > 0.91, RMSE < 360 kg ha(-1)). Additionally, RF and KNN accuracy remained high (R-2 > 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.

Automated summary

This study presented two modeling approaches for estimating durum wheat yield based on Sentinel-2 data, with machine learning algorithms showing high accuracy for early yield prediction, which is essential for precision agriculture applications.