Abstract
The postharvest preservation of fresh produce is crucial for enhancing food sustainability and security. The study investigates the combined effects of coating with gum Arabic (GA), storage temperature, and packaging methods on the quality of Barhi date during storage. In addition, the artificial neural network (ANN) model was used to predict fruit quality parameters, including fruit weight, volume, density, weight loss, hardness, decay percentage, moisture content, pH, Total soluble solid, water activity, color parameters, color difference, and browning index based on the coating and storage conditions and the initial fruit weight, size, moisture content, total soluble solids, and color parameters at the beginning of storage. The findings indicated that vacuum packaging, coating with 10 % GA concentration, and cold storage were the most effective combinations for prolonging shelf life and preserving the quality parameters of stored Barhi dates. The implemented ANN model effectively predicted most fruit quality parameters, closely corresponding with observed data across various storage environments, as indicated by the low values of the evaluation metrics, i.e., mean absolute error, mean absolute percentage error, relative error, and root mean squared error. The R(2) values observed for the quality parameters of fruit weight (0.951), volume (0.746), density (0.735), weight loss (0.989), hardness (0.967), decay percentage (0.962), moisture content (0.901), pH (0.965), total soluble solids (0.973) water activity (0.859), and color parameters of L∗ (0.978), a∗ (0.784), b∗, ΔE∗ (0.955), and browning index (0.951), validate the precision and dependability of the ANN models in their ability to predict the quality attributes of Barhi date fruits. The study outcomes contribute to food quality and supply chain management by finding the best combination of edible GA coating and storage conditions. Inaddition, predicting fruit quality during storage helps maintain their quality and reduce postharvest losses.