.png){kind=icon}
.png){kind=icon}
Return
Explainable machine learning reveals water-related drivers of sub-field dryland wheat yield variability
.png){kind=icon}
OA
AI
M
S
K
T
M
H
DOI：10.1016/j.eja.2026.128296.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Interpretable ML framework quantifies sub-field dryland wheat yield drivers. • Water variables dominate yield variability across management systems. • Deep soil moisture, topography, and nitrogen zone explain key spatial yield patterns. • Spatial validation improves understanding of model generalization across fields. • The proposed framework enables targeted, early-season precision management decisions.
Keywords:
Precision agriculture
Decision making
Crop yield
Environmental and management drivers
XGBoost
SHAP
Journal
IF:
5.5
Papers:
605
Citations:
1.3W
Organization
Cited Papers