Bioactive Compound Recovery from Apple Pomace by Aqueous Ultrasound-Assisted Extraction: Machine Learning Modelling and Multi-Objective Optimization

Apple pomace represents a sustainable source of phenolic compounds with significant antioxidant potential. This study investigated the recovery of water-extractable bioactive constituents from apple pomace using aqueous ultrasound-assisted extraction (UAE) combined with biochemical profiling and machine learning-based modelling. Extraction conditions were varied according to time (10–30 min), temperature (25–75 °C), and solvent-to-solid ratio (10–20 mL/g). The obtained extracts were evaluated for total phenolic content (TP), total flavonoid content (TF), antioxidant capacity (DPPH, ABTS, CUPRAC, FRAP, metal chelating, and phosphomolybdenum assays), and enzyme inhibitory activities against acetylcholinesterase, butyrylcholinesterase, tyrosinase, α-amylase, and α-glucosidase. TP and TF ranged from 4.70 to 9.97 mg GAE/g and 0.21–0.79 mg RE/g, respectively, while antioxidant assays demonstrated substantial variation depending on extraction conditions. Strong correlations (r = 0.827–0.945, p < 0.001) were observed between phenolic content and antioxidant activity. Artificial neural networks, random forests, support vector machines, and a hybrid ensemble model were applied to predict extraction outcomes, with predictive performance varying substantially among biochemical responses and modelling approaches. Multi-objective optimization using the NSGA-II formulation identified a representative Pareto compromise at approximately 15.1 min, 25.7 °C, and a solvent-to-solid ratio of 13.7 mL/g, balancing desirable biochemical responses with processing requirements.