Dataset

In this study, the effects of morphological characteristics on the fresh herbage yield of sorghum x sudangrass hybrid grown under different irrigation levels in Konya were analyzed using various data mining methods, including Artificial Neural Networks (ANN), Automatic Linear Model (ALM), Random Forest (RF), and Multivariate Adaptive Regression Spline (MARS) algorithms. Descriptive statistics such as plant height, stem diameter, and crude protein content were calculated, and model fit was evaluated using metrics like R², RMSE, and MAPE. The results demonstrated that the MARS algorithm, with the lowest error values and the highest fit (R² = 0.995), was the best model for predicting fresh herbage yield. These findings indicate that the MARS algorithm provides a strong alternative to other methods.