Machine Learning assisted design of tailor‐made nanocellulose films: A combination of experimental and computational studies

Abstract

Nowadays, modern nanomaterial research is complemented by machine learning methods to reduce experimental costs and process time. With this motivation, here, we implemented artificial neural network (ANN), random forest (RF), and multiple linear regression (MLR) methods to predict the mechanical properties of threecomponent nanocomposite films consisting of polyvinyl alcohol (PVA) crosslinked 2,2,6,6-tetramethylpiperidine-1-oxyl (TEMPO) oxidized cellulose nanofibers (TOCNFs) and either ammonium zirconium carbonate (AZC) or glyoxal (Gx) using the mechanical properties of mono-component TOCNF films and two-component nanocomposites containing PVA, AZC, or Gx-crosslinked TOCNF as the input of prediction system. Prediction methods were evaluated with performance indicators and experimental data. Overall, MLR performed with least accuracy, whereas ANN prediction displayed the lowest error followed closely by RF. Additionally, the physically or/and chemically crosslinked hybrid films with optimized amount of crosslinkers resulted in structures with a strength to rupture that was significantly higher than that of the pure nanocellulose films (increases of up to~90% in tensile strength and~70% in Young's modulus). POLYM. COM-POS., 40:4013-4022, 2019.

Mechanics Design in Cellulose‐Enabled High‐Performance Functional Materials

“…TEMPO‐mediated oxidation, a common method used to isolate TEMPO‐NFCs from plants, is expensive thus impeding a low‐cost product development. To address that, enzymatic treatments [ 51,147 ] may be used along with novel computational techniques driven by machine learning algorithms [ 148,149 ] to minimize the experimental cost in materials design and optimization. Furthermore, the studies to tune the mechanical performance of cellulose based materials by overcoming its hydrophilicity and reaching a high value of wet strength are still limited.…”

Physically soft magnetic films and devices: fabrication, properties, printability, and applications

“…These approaches will generate a huge set of data that can be subjected to machinelearning based approaches, eventually opening up avenues to investigate unexplored combinations of materials that lead to soft, magnetic inks and films with outstanding properties. Such machine learning based approaches for fabricating novel materials (especially nanocomposites with desired properties) have received a lot of attention recently; 163,[184][185][186][187][188][189][190] this will be one of the first approaches for fabricating novel soft, magnetic inks and films using machine learning. The third critical aspect that deserves significant attention is the flexibility in fabricating devices and components of various shapes using such soft magnetic inks and films.…”

A Review of Applications Using Mixed Materials of Cellulose, Nanocellulose and Carbon Nanotubes

“…In addition, there are also reports of simulations on mixed materials of NC and CNTs [136,137]. In recent years, as a result of remarkable improvements in computer performance, many researches on NC or CNTs using machine learning have been reported [138][139][140][141][142][143][144]. In the future, research using these machine learning methods will accelerate the development of further mixed materials of cellulose and CNTs research, such as by reducing the time and cost of experiments.…”