Quercus cerris L. wood chips extraction optimization: a comparative study between full factorial design (FFD) and artificial neural network (ANN)

The search for sustainable sources of antioxidants has driven research into underutilized biomasses [ 1 ], such as Quercus cerris L. wood chips (QC). While established statistical methods like Full Factorial Design (FFD) are commonly employed for process optimization, applying advanced computational techniques, mainly Artificial Neural Networks (ANN), presents a promising approach for potentially more effective extraction process modeling. This research was designed to optimize the extraction of QC antioxidant compounds, comparing the predictive effectiveness of FFD and ANN approaches. Experimental data from extractions obtained by varying temperature (20-50-80°C), solvents (0-20-40%EtOH/H2O), and time (3-6-24 h) were used to build and train an ANN model. The trained ANN exhibited a higher ability to predict antioxidant activity values based on the input variables than FFD, highlighting ANN’s capability to capture intricate, non-linear relationships within the results obtained from all the extraction processes. Specifically, ANN achieved a stronger correlation (R 2 =0.92, 0.96, 0.91 for DPPH, FRAP, and TPC) than FFD (R 2 =0.83, 0.79, 0.75 for DPPH, FRAP, and TPC) between predicted data and experimental outcomes. Furthermore, ANN demonstrated comparable ability to FFD in optimizing the extraction condition (80°C, 24h, 40%EtOH for FFD and 80°C 23.47h, 39.32% EtOH for ANN) [ 2 ]. These findings strongly support using ANN as a highly effective tool for optimizing the extraction of valuable antioxidants from plant matrices. The high degree of predictive accuracy demonstrated by the ANN model suggests its superiority in understanding and modeling the complex interactions of extraction parameters compared to traditional statistical approaches like FFD. Publication History Article published online: 05 March 2026 © 2026. Thieme. All rights reserved. Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany