About this document

Hybrid CNN-LSTM & XGBoost for Crop Yield by aladin.oldest is a document available to read on EtoBox.

This study compares hybrid models, specifically CNN-LSTM and XGBoost, for predicting global crop yields using climate and pesticide data, emphasizing the need for explainability through SHAP. The results indicate that Random Forest outperforms both XGBoost and CNN-LSTM, while the hybrid model struggled due to data constraints. Key findings highlight rainfall as the most critical driver of crop yield, suggesting future research should integrate additional data sources for improved accuracy.

Author

aladin.oldest

Language

EN