RMSE, MAE and R2 of the models using 5-fold CV.

Understanding accurate methods for predicting yields in complex agricultural systems is critical for effective nutrient management and crop growth. Machine learning has proven to be an important tool in this context. Numerous studies have investigated its potential for predicting yields under different conditions. Among these algorithms, Random Forest (RF) has gained prominence due to its ability to manage large data sets with high dimensions, as well as its ability to uncover complicated non-linear relationships and interactions between variables. RF is particularly suitable for scenarios with categorical variables and missing data. Given the complex web of management practices and their nonlinear effects on yield prediction, it is important to investigate new machine learning algorithms. In this context, our study focused on the evaluation of gradient boosting methods, particularly Extreme Gradient Boosting (XGB) and Gradient Boosting Regressor (GBR), as potential candidates for yield estimation of the maize hybrid Zhengdan 958. Our aim was not only to evaluate and compare these algorithms with existing approaches, but also to comprehensively analyze the resulting model uncertainties. Our approach includes comparing multiple machine learning algorithms, developing and selecting suitable features, fine-tuning the models by training and adjusting the hyperparameters, and visualizing the results. Using a recent dataset of over 1700 maize yield data pairs, our evaluation included a spectrum of algorithms. Our results show robust prediction accuracy for all algorithms. In particular, the predictions of XGB (RMSE = 0.37, R2 = 0.87 and MAE = 0.26) and GBR(RMSE = 0.39, R2 = 0.86 and MAE = 0.27), emphasized the central role of weather characteristics and confirmed the high dependence of crop yield prediction on environmental attributes. Utilizing the capabilities of gradient boosting for yield prediction holds immense potential and is consistent with the promise of this method to serve as a catalyst for further investigation in this evolving field