Explainable machine learning-based prediction of shelf-life and anthocyanin accumulation in table grapes

Grapes (Vitis vinifera L.) are recognized as the third most popular fruit worldwide. Nevertheless, table grapes are highly perishable. Accurate prediction of shelf-life duration and nutritional components is crucial in supply chain of fresh fruit and vegetables. In present study, we developed the machine learning models to predict the shelf-life and total anthocyanin content (TAC) of table grapes intelligently. The artificial neural network (ANN) accurately estimated shelf-life, with a mean absolute error (MAE) of 1.624 days and a coefficient of determination (R²) of 0.9873, whereas extreme gradient boosting (XGBoost) effectively predicted TAC (MAE 0.0113 mg C3G g^-1； R² 0.9355). SHapley Additive exPlanations (SHAP)-based sensitivity analysis revealed the berry abscission rate, weight loss rate and postharvest treatment were critical factors influencing quality performance, improving model interpretability. These findings successfully provide a reliable approach for monitoring grape quality, providing novel insight into reducing the loss of fresh agricultural produce.