.png){kind=icon}
.png){kind=icon}
Return
Deciphering eggplant yield prediction in West Bengal by an explainable AI-based stacking ensemble framework
.png){kind=icon}
OA
AI
S
A
A
M
A
R
B
DOI：10.1016/j.jafr.2026.103170.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Glmnet-based stacked ensemble provided robust temporal yield predictions but demonstrated limited spatial transferability, • LOYO based nested cross validation framework prevented temporal data leakage and reduce bias in yield prediction models, • SHAP analysis revealed, yield was primarily driven by soil (44.9%) followed by weather variables (29.2%), hydroclimatic indices (22.1%) and engineered biophysical interactions (3.7%). • Soil water holding capacity (WHC) and nitrogen (N) emerged as the most dominant factors affecting yield prediction across the majority of districts. • District-level analysis identified distinct regional prediction contributors, emphasizing role of context specific factors in yield prediction.
Keywords:
Eggplant yield prediction
Machine learning
Stacked ensembles
Agro-climatic variability
Explainable AI
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.2
Papers:
3.3K
Citations:
6.5K
Organization
Cited Papers