Lignocellulosic biomass, particularly softwoods such as pine, poses a significant challenge to enzymatic hydrolysis due to its high lignin content and complex structural rigidity. Although the application of steam explosion and alkaline pretreatment has gained widespread popularity for enhancing digestibility, the optimization of process parameters remains a formidable challenge due to the nonlinear interactions among variables. Machine learning is emerging as a promising solution to address these challenges, offering a viable alternative for predictive modeling and process control. In this study, an artificial neural network (ANN) model was developed to predict the enzymatic hydrolysis rate of steam-exploded pine wood subjected to mild alkaline (NaOH) pretreatment. The artificial neural network (ANN) was trained on experimental data encompassing three primary process variables: steam explosion time (1 to 5 min), NaOH concentration (0.5 to 2.0%), and chemical pretreatment time (12 to 24 h). The artificial neural network (ANN) model demonstrated the highest level of accuracy among the models evaluated, including random forest, support vector machine, and extreme gradient boosting. It attained a coefficient of determination (R²) of 0.9805. In conditions that were not optimized (1% NaOH, 24-hour treatment, 5 min steam explosion, without bark), a maximum hydrolysis of 93.9% was obtained.

This research focused on producing water-soluble carbohydrates extracts from the leaves of the wild plant <i>Cacalia firma</i> using commercial enzymatic processes. Different enzymes and conditions were applied to the leaves to determine the optimal method for extracting carbohydrates. Enzymes used were Cellic CTec3 HS, Celluclast 1.5 L, Viscozyme L, Pectinex ultraSP-L, and Amylase AG. Pectinase, cellulase, and other enzymes are isolated from yeast, bacteria, or some higher plants and are commonly used to break down pectin, which is the cell wall or intercellular connective tissue in plant tissues, to soften fruit or vegetable tissues and to make sugars. They are commonly used to soften the tissues of fruits and vegetables, to produce sugars, or to increase the yield of juice in fruit processing. The resulting water-soluble carbohydrates demonstrated significant antioxidant capabilities in vitro, as evidenced by DPPH radical-scavenging and ABTS assays. Furthermore, the carbohydrates exhibited high levels of total polyphenol and flavonoid content. The extraction methodology was fine-tuned using response surface methodology alongside the Box-Behnken design, achieving a maximum carbohydrate yield of 129.7 mg/g, which was very close to the predicted value of 132.4 mg/g. The optimal conditions included an extraction temperature of 47.3 °C, a duration of 63 h, and a pH of 3.7 using Viscozyme L. This study offers a theoretical foundation for the development of natural carbohydrate antioxidants and lays the groundwork for large-scale production and utilization of <i>C. firma</i> leaf carbohydrates. These extracts, showing antioxidant activity, hold potential as functional ingredients in the food industry.