Stacked Ensemble Learning for Chickpea Yield Prediction Using Meteorological and Soil Data

This study proposes a stacked ensemble regression model for predicting annual chickpea yield based on agro-meteorological and soil data collected from six provinces in Turkey's Central Anatolia Region between 2004 and 2024. The training was carried out using Ridge Regression, Lasso Regression, and XGBoost, and the outputs of these models were combined using a Ridge meta-regressor. Input variables included log-transformed yield values, meteorological indicators (such as wind speed, temperature, humidity, and soil moisture), annual production quantities, and soil fertility parameters (nitrogen, phosphate, potassium). The dataset was split into 80% for training and 20 % for testing. On the test data, the model achieved an $\mathbf{R}^{\mathbf{2}}$ score of $\mathbf{0. 9 1 3}$, a MAE of $\mathbf{0. 0 9 9}$, and an RMSE of 0.164, indicating high accuracy and strong generalization capability. This study demonstrates the effectiveness of ensemble learning methods for precision agriculture and offers a scalable solution for chickpea yield prediction under semi-arid conditions.