Artificial intelligence-driven validation of silver and titanium nanomaterials impact on morpho-chemical potential of industrial hemp (Cannabis sativa L.)
摘要
The aim of this research was to assess the effect of titanium nanoparticles (TiO2NPs) and silver nanoparticles (AgNPs) on in vitro seedling emergence, seedling growth, and biochemical parameters of hemp Cv. Narlı. The seeds were introduced to different concentrations (0, 200, 400, 800, 1200, 1600 mg/L) of both nanoparticles, incorporated into the culture medium. The results showed that AgNPs supplementation had a positive effect on shoot length, root length, total length, fresh weight, chlorophyll-a (Chl-a), chlorophyll-b (Chl-b), total carotenoids (Car), and malondialdehyde (MDA). The greatest increase in seedling (%) and shoot:root ratio was recorded from the medium containing TiO2NPs. Furthermore, the supplementation of 800 mg/L AgNPs led to the highest outcomes in terms of root length, total length, and fresh weight. The values for Chl-a, Chl-b, and Car showed no significant variations, reaching their highest points in the medium supplemented with 1600 mg/L NPs. While MDA levels were also not statistically significant and maximum scores were noted at different doses of both NPs. The results were examined by generating a Pareto chart to discern the key influencing factors, and the response optimizer was applied to identify an optimal solution for the combinations of input variables. Finally, the Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Multilayer Perceptron (MLP) based supervised machine learning models were employed to predict and verify the obtained results using three distinct performance criteria. The MLP model, overall, demonstrated superior performance in validation and prediction compared to RF and XGBoost, respectively.
Graphical abstract