Enhancing Agricultural Decision-Making: Banana Yield Forecasting in Colombia Using Tuned Ensemble Machine Learning Models

Full abstract

Read the full abstract

Accurate short-term forecasts of banana productivity can improve harvest scheduling, packing-capacity allocation, and export logistics, yet commercial forecasts often deviate substantially from realized yields. Objective: We evaluated whether tuned ensemble machine learning could reduce that error for seven-week-ahead forecasting of weekly productivity (boxes/Ha). Methods: Using weekly records from nine commercial farms in northern Colombia (2007–2018), we benchmarked six tuned ensembles—Random Forest, Extra Trees, Gradient Boosting, LightGBM, XGBoost, and CatBoost—against a company forecast and three statistical baselines (Seasonal Naive, Historical Mean, and a per-farm ARIMA). Hyperparameters were tuned by time-series cross-validation on 2007–2017, and models assessed on a 2018 holdout (405 observations). Results: CatBoost obtained the lowest errors (MAE = 3.95, R2 = 0.61), a 57.0% MAE and 81.2% MSE reduction versus the company baseline (MAE = 9.18, R2 = −1.06). Bootstrap 95% CIs and the Diebold–Mariano test showed CatBoost, XGBoost, LightGBM, Gradient Boosting, Random Forest, and the Historical Mean to be statistically equivalent (CatBoost’s lead was not significant), all outperforming the ARIMA (MAE = 5.64), Seasonal Naive (MAE = 7.31), and company baselines; an ablation confirmed no data leakage. Conclusions: Tuned ensembles can substantially improve short-term harvest planning in commercial banana production, with model choice guided by operational and computational constraints.