Enhancing Fig Fruit Shelf Life Through Biopolymer-Based Coatings: Predicting Postharvest Quality Preservation Using an Advanced XG-Boost Machine Learning Approach

Figs (Ficus carica L.) are rich in nutrients and bioactive compounds that support human health. However, they are highly susceptible to postharvest spoilage due to their delicate and perishable nature. This vulnerability highlights the need for innovative preservation technologies to maintain their quality. The present study investigated the cumulative effect of 1‑methylcyclopropene (1‑MCP), an edible coating composed of Aloe vera (Aloe barbadensis Mill.) gel (AV) and chitosan (CH) on the quality of fresh figs (cv. ‘Brown Turkey’) during storage at 2°C ± 1 and 80–85% relative humidity (RH). Various physicochemical and biochemical analyses were performed every week. The microbial load was assessed on both the first and last days of storage. The treatments significantly decreased fruit weight loss and decay and suppressed total microbial counts, while also improving fruit firmness. The activities of polyphenol oxidase (PPO) and peroxidase (POD) were lower in treated fruits at the end of storage as compared to the control. Furthermore, the treatments reduced respiration and ethylene production, preserved total phenolic and flavonoid contents in the fruits. The results indicate that the combined 1‑MCP and AV/CH treatments improved fig quality and shelf life till 21 days under cold storage, compared with a markedly shorter shelf life in control fruits. The obtained quality attributes were used to develop a shelf‑life machine learning prediction model based on Extreme Gradient Boosting (XGBoost). This model provides an initiative for linking treatments and quality indicators with shelf life facilitating future efforts to optimize storage strategies for fresh fig fruit.