Utilizing AI algorithms to model and optimize the composite of nanocellulose and hydrogels via a new technique.

Plants, various biological organisms, and certain marine organisms typically provide biopolymers, like cellulose. Some things that make them unique are that they are non-toxic, biodegradable, have high specific strength and specific modulus, are easy to change the surface of, are highly hydrophilic, and are biocompatible. Significantly, nanocellulose has emerged as a prominent development in the 21st century. The objective of this work was to create a model that can accurately predict and optimize the viscosity, storage modulus (G'), and loss modulus (G″) of sulfate nanocellulose (S-NC) hydrogen materials. These properties were analyzed in different experimental settings. To do this, the researchers used the RSM and multi-layer perceptron (MLP)-ANN techniques to accurately represent and optimize the viscosity, G', and G″ properties. Ultimately, the researchers conducted RSM optimization to identify the optimal patterns of viscosity, G', and G″ characteristics for a new method of producing nanocellulose materials. The results showed that the ANN and RSM methods were very good at predicting how nanocellulose hydrogels would behave while nanocellulose products were being made. Moreover, the ANN technique exhibited superior accuracy in forecasting processes' G' and G' behavior compared to the RSM method. Ultimately, the ideal viscosity state was attained by using a shear rate value of 95 S and including 1.5 wt% of S-NC. The optimal mode for G' and G″ was achieved at a frequency of 14.532 Hz and an S-NC concentration of 1.468 wt%.