Scholarlink

Precise crop yield estimation is crucial for food security and effective agricultural planning. The research here suggests a machine learning method in the form of a stacking ensemble model with base learners Random Forest, XGBoost, and CatBoost, and Ridge Regression as the final learner. A global dataset containing climate information, agricultural information, and economic information was preprocessed with common scaling and one-hot encoding and split 80:20 into training and testing. The ensemble performed better than all of the individual models with an RMSE of 9309.04, MAE of 3576.41, and \(\hbox {R}^{2}\) of 0.9881. The outcomes demonstrate the efficiency of stacking models in enhancing prediction accuracy and facilitating data-driven agriculture.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Stacked Ensemble Learning for Global Crop Yield Prediction: A Comparative Study of Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mohd Anas,
  • Amandeep Kaur

摘要

Precise crop yield estimation is crucial for food security and effective agricultural planning. The research here suggests a machine learning method in the form of a stacking ensemble model with base learners Random Forest, XGBoost, and CatBoost, and Ridge Regression as the final learner. A global dataset containing climate information, agricultural information, and economic information was preprocessed with common scaling and one-hot encoding and split 80:20 into training and testing. The ensemble performed better than all of the individual models with an RMSE of 9309.04, MAE of 3576.41, and \(\hbox {R}^{2}\) of 0.9881. The outcomes demonstrate the efficiency of stacking models in enhancing prediction accuracy and facilitating data-driven agriculture.