Feature Engineering Based Climate-Driven Crop Yield Prediction
Contributors
Dr Kapil Keshao Wankhade
Dr Ganesh Khekare
Keywords
Proceeding
Track
General Track
License
Copyright (c) 2026 Sustainable Global Societies Initiative

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Abstract
Food security, sustainable resource management, and agricultural planning all depend on proper prediction of crop yield. This paper suggests a machine learning model for predicting wheat crop yields based on previous agricultural data that includes parameters like the size of the cultivation area, production volume, and area characteristics. First, data cleaning and categorical variable encoding were used as data preprocessing techniques to enhance the quality of data and model performance. Three regression models, such as Linear Regression (LR), Support Vector Regression (SVR), and Random Forest (RF), were used to model the relationship between the input features and the wheat yield. Besides, a hybrid ensemble model was created by integrating the individual model predictions to improve the predictive power. The results of the experiment show that the suggested hybrid ensemble model performs much better than the corresponding models, showing the lowest RMSE (122.42) and MAE (59.80) and the highest R2 (0.987). The findings show that ensemble learning has the potential to significantly enhance the quality of crop yield prediction and offer useful decision support to agricultural planning and management.