A comparative study of centrifugal fertilizer spread using generalized additive model, random forest and polynomial regression

With increasing fertilizer use, precise control of granular spreading is essential to reduce environmental impacts and improve agronomic efficiency. This study presents a reliable approach that predict particle trajectories, and the resulting swath width by modeling particle velocity and landing position from centrifugal spreader discs, thereby eliminating the need for time-consuming bin-based field tests. Particle velocity and travel distance data were generated using validated, physics-engine based Extended Discrete Element Method (EDEM) simulations. A realistic spreader geometry, calibrated material properties, and aerodynamic drag were incorporated. The EDEM model was experimentally validated with validation errors ranging between 2% and 6%. Nonlinear polynomial regression models of varying orders and Generalized Additive Models (GAMs) were compared with a non-parametric Random Forest (RF) model to predict particle velocity and position. Model performance was assessed using $$\textrm{RMSE}$$ , $$R^2$$ , $$\textrm{AIC}$$ , and $$\textrm{BIC}$$ . The results show that Generalized Additive Models (GAMs) consistently outperformed Random Forest (RF) and polynomial regression models, in terms of accuracy with high interpretability. RF ranked as the second-best performing model. The optimal GAM achieved an $$R^2$$ = 0.98 ( $$\textrm{RMSE}$$ = 0.27) for velocity prediction and an $$R^2$$ = 0.93 ( $$\textrm{RMSE}$$ = 0.27) for position prediction. External validation using an independent EDEM dataset further confirmed the generalizability of the models, yielding an $$R^2$$ = 0.98 ( $$\textrm{RMSE}$$ = 0.35) for velocity and an $$R^2$$ = 0.93 ( $$\textrm{RMSE}$$ = 0.49) for position. In addition, deviance contribution analysis from the GAM models and scaled variable importance from the Random Forest model both identified time, wind flow, disc speed, and traveling speed as the four most influential variables in predicting both response variables. GAMs trained using EDEM simulation data provided a robust framework for predicting fertilizer granule trajectories and estimating resulting swath width. These results support future data-driven precision agriculture for improved efficiency for fertilizer application. • A simulation-informed framework was developed to model fertilizer granule velocity and position. • EDEM simulations are proven, physic-engine based simulation providing accurate data for particle motion under diverse operational and environmental conditions. • Disc speed, wind flow, time, and traveling speed were identified as dominant factors influencing particles trajectory. • Trained models (GAM, RF, and polynomial regression) used EDEM simulation data that was validated using tray-based experiments to ensure accuracy and precision. • The proposed approach enables efficient estimation of swath width, (twice the maximum traverse distance), and particle velocity without relying on labour-intensive and time-consuming bin-based field experiments or image-based methods where particle counting or tracking are sensitive to occlusion and errors. This study contributes to precision agriculture by developing a simulation-informed, data-driven framework for predicting fertilizer particle trajectories (velocity and position) and estimating the corresponding swath width using EDEM simulations and advanced modeling. These models include polynomial regression, Generalized Additive Modeling (GAM) and Random Forest (RF). The proposed approach develop predictive models and enables ranking key design, operational, and environmental parameters influencing particle motion. These capabilities provide valuable insights into fertilizer distribution behavior and may support future improvements in site-specific nutrient management and application strategies.