@article{article_1787194, title={Estimating Bell Pepper Leaf Area: A Comparative Study of Machine Learning Models Under Varying Irrigation Levels}, journal={Bahçe}, volume={54}, pages={133–143}, year={2025}, author={Tunca, Emre and Köksal, Eyüp Selim}, keywords={Yaprak Alan İndeksi, Makine Öğrenmesi, Dolmalık Biber, Sulama, MLP}, abstract={Leaf Area (LA) is a critical parameter for crop monitoring and evapotranspiration estimation. This study aimed to estimate bell pepper LA values using different machine learning (ML) models and to evaluate the effect of different irrigation levels on model performance. Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) were used as ML algorithms. In order to obtain a large data set, the LA values of bell pepper grown at four different irrigation levels were used. In this context, a 2-year field trial was conducted. LA values from the first year (2017) were used in the training of the models (6757 samples), while LA values from the second year (2018) (6128 samples) were used as test data. According to the results of this study, MLP (R2=0.9, RMSE=0.2 cm2 and MAE=0.15 cm2) showed the highest performance among used ML algorithms, while XGBoost (R2=0.9, RMSE=0.2 cm2 and MAE=0.15 cm2) showed the lowest performance. Moreover, similar performances were obtained when LA values obtained from different irrigation levels were evaluated separately. The results show that ML methods can estimate LA quickly and accurately as an alternative to traditional methods.}, number={2}, publisher={Atatürk Bahçe Kültürleri Merkez Araştırma Enstitüsü}, organization={Ondokuz Mayıs University}