Erdinç Savaşlı
Research Subjects
Research Interests
Erdinç Savaşlı has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ali Volkan Bilgili
Harran Universitesi
1 shared publication - Amjad Mohamed Ismael
Department of Soil Science and Plant Nutrition, Faculty of Agriculture, Harran University, Sanliurfa, Turkey
1 shared publication - Irfan Ozberk
Department of Field Crops, University of Harran, 63300 Sanliurfa, Türkiye
1 shared publication - João Pedro Matos Carvalho
Universidade de Lisboa
1 shared publication - Salih Aydemir
Harran University
1 shared publication - Süreyya Betül Rufaioğlu
Department of Soil Science and Plant Nutrition, Faculty of Agriculture, Harran University, Şanlıurfa 63300, Türkiye
1 shared publication
Latest Publications
- Open Access
- 12 July 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (14) , 2416
Sensor-Based Yield Prediction in Durum Wheat Under Semi-Arid Conditions Using Machine Learning Across Zadoks Growth Stages
Yield prediction in wheat cultivated under semi-arid climatic conditions is gaining increasing importance for sustainable production strategies and decision support systems. In this study, a time-series-based modeling approach was implemented using sensor-based data (SPAD, NSPAD, NDVI, INSEY, and plant height measurements collected at four different Zadoks growth stages (ZD24, ZD30, ZD31, and ZD32). Five different machine learning algorithms (Random Forest, Gradient Boosting, AdaBoost, LightGBM, and XGBoost) were tested individually for each stage, and the model performances were evaluated using statistical metrics such as R2%, RMSE t/ha, and MAE t/ha. Modeling results revealed that the ZD31 stage (first node detectable) was identified as the most successful phase for prediction accuracy, with the XGBoost model achieving the highest R2% score (81.0). In the same model, RMSE and MAE values were calculated as 0.49 and 0.37, respectively. The LightGBM model also showed remarkable performance during the ZD30 stage, achieving an R2% of 78.0, an RMSE of 0.52, and an MAE of 0.40. The SHAP (SHapley Additive exPlanations) method used to interpret feature importance revealed that the NDVI and INSEY indices contributed the most significant values to prediction accuracy for yield. This study demonstrates that phenology-sensitive yield prediction approaches offer high potential for sensor-based digital applications. Furthermore, the integration of timing, model selection, and explainability provided valuable insights for the development of advanced decision support systems.
- 12 July 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (14) , 2416
Open AccessSensor-Based Yield Prediction in Durum Wheat Under Semi-Arid Conditions Using Machine Learning Across Zadoks Growth Stages
Yield prediction in wheat cultivated under semi-arid climatic conditions is gaining increasing importance for sustainable production strategies and decision support systems. In this study, a time-series-based modeling approach was implemented using sensor-based data (SPAD, NSPAD, NDVI, INSEY, and plant height measurements collected at four different Zadoks growth stages (ZD24, ZD30, ZD31, and ZD32). Five different machine learning algorithms (Random Forest, Gradient Boosting, AdaBoost, LightGBM, and XGBoost) were tested individually for each stage, and the model performances were evaluated using statistical metrics such as R2%, RMSE t/ha, and MAE t/ha. Modeling results revealed that the ZD31 stage (first node detectable) was identified as the most successful phase for prediction accuracy, with the XGBoost model achieving the highest R2% score (81.0). In the same model, RMSE and MAE values were calculated as 0.49 and 0.37, respectively. The LightGBM model also showed remarkable performance during the ZD30 stage, achieving an R2% of 78.0, an RMSE of 0.52, and an MAE of 0.40. The SHAP (SHapley Additive exPlanations) method used to interpret feature importance revealed that the NDVI and INSEY indices contributed the most significant values to prediction accuracy for yield. This study demonstrates that phenology-sensitive yield prediction approaches offer high potential for sensor-based digital applications. Furthermore, the integration of timing, model selection, and explainability provided valuable insights for the development of advanced decision support systems.