2026 Volume 26 Issue 3 Pages 101-106
Cellulose nanofibers (CNFs) exhibit broad and multimodal morphology distributions, for which mean descriptors alone are often insufficient to explain the properties of polymer composites. This issue is particularly pronounced for mechanically fibrillated CNFs, where coarse fractions and fine fibrils coexist and cause large variability in material performance. This review overviews a data driven analytical framework that combines optical sedimentation profiling with machine learning to rapidly and non destructively estimate specific surface area (SSA) and morphology related distribution information from sedimentation behaviors. Sedimentation profiles are represented as velocity indices and spatiotemporal heatmaps, which are analyzed using gradient boosting regression and convolutional neural networks to predict SSA with high accuracy. Furthermore, sedimentation heatmaps are exploited to infer aspect ratio distributions, enabling separation of coarse and fine fractions. By integrating the inferred morphology descriptors with chemical information derived from IR spectroscopy, the impact strength of polypropylene (PP)/CNF composites can be quantitatively explained. This approach enables composite design that explicitly considers morphology distributions and provides a practical materials DX platform for quality control, process development, and data driven materials selection.
