What question did this study set out to answer?

This study aims to assess the viability of using multi-temporal Sentinel-2 imagery for accurate wheat yield estimation in commercial fields.

May 16, 2026Open Access

Operational Wheat-Yield Estimation in the Eastern Mediterranean Using Multi-Temporal Sentinel-2 Imagery and Explainable Machine Learning

Puntos clave

This study aims to assess the viability of using multi-temporal Sentinel-2 imagery for accurate wheat yield estimation in commercial fields.
Evaluated six regression algorithms: Random Forest, Support Vector Regression, KNN, Decision Tree, LASSO regression, and Gaussian Process Regression.
Used combine-harvester yield maps as ground-truth observations across nine wheat fields in Ptolemaida, Greece, during the 2023–2024 growing season.
Performed Leave-One-Field-Out cross-validation and applied SHAP for model interpretation.
Random Forest achieved the highest predictive accuracy with a MAPE of 7.90% and RMSE of 45.15 kg decare−1 under the raw spectral bands configuration.
Statistically significant improvement found in Random Forest over Decision Tree and KNN models (p<0.05).
Model predictions were influenced mainly by specific spectral bands during late grain filling and maturity phases.

Resumen

Accurate field-scale wheat yield estimation is essential for precision agriculture, farm-level decision-making, and food security planning. However, operational studies conducted under real commercial farming conditions in the eastern Mediterranean remain limited. This study investigated whether multi-temporal Sentinel-2 imagery could support reliable wheat yield estimation across nine commercial wheat fields near Ptolemaida, Greece, during the 2023–2024 growing season. Both durum and common wheat fields were included, and combine-harvester yield maps were used as ground-truth observations. Six regression algorithms—the Random Forest (RF), Support Vector Regression (SVR), k-nearest neighbors (KNN), Decision Tree (DT), LASSO regression, and Gaussian Process Regression (GPR) algorithms—were evaluated using three feature configurations: raw Sentinel-2 spectral bands only (Sentinel-only (SO)), spectral bands combined with vegetation indices (Sentinel+Indices, SI), and vegetation indices only (Indices-only, IO). Model generalization was assessed through a strict Leave-One-Field-Out (LOFO) cross-validation protocol, and the method of SHapley Additive exPlanations (SHAP) was used to interpret model behavior and identify the most influential spectral regions and phenological stages. RF achieved the highest predictive accuracy, with a MAPE of 7.90% and an RMSE of 45.15 kg decare−1 under the SO configuration, demonstrating a statistically significant improvement over DT and KNN models (p<0.05). SHAP analysis indicated that model predictions were mainly driven by SWIR-1, NIR-narrow, and red-edge bands acquired during late grain filling and maturity, while vegetation indices contributed limited additional information. These findings suggest that raw multi-temporal Sentinel-2 spectral bands are highly effective for field-scale wheat yield estimation within the scope of this study, although further validation across diverse growing seasons and geographic regions is required to confirm broad operational sufficiency.

Leer artículo completoexternamente

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo