Related Concept Videos
Polymers: Molecular Weight Distribution
Molecular Weight of Step-Growth Polymers
As the step-growth polymerization involves step-wise condensation of monomers, the molecular weight also builds up eventually. Consequently, high molecular weight polymers are obtained at the late stages of the polymerization, where 99% of monomers have been consumed.
The extent of the...
Polymer Classification: Crystallinity
Crystalline domains are the regions where polymer chains are aligned in an orderly manner and held together in proximity by intermolecular forces. For example, chains in the crystalline domains of polyethylene and nylon are bound together by van der Waals...
Molecular Models
Polymers: Defining Molecular Weight
The number average molecular weight (Mn) is the summation of the number...
Ziegler–Natta Chain-Growth Polymerization: Overview
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
The responsive behaviors of bilayer membrane under uniaxial mechanical probe.
Self-assembly of phospholipid molecules in solutions under shear flows: Microstructures and phase diagrams.
Light-responsive expansion-contraction of spherical nanoparticle grafted with azopolymers.
Related Experiment Video
Updated: Dec 7, 2025

DNA Nanotubes as a Versatile Tool to Study Semiflexible Polymers
Published on: October 25, 2017
Neural network model for structure factor of polymer systems.
Jie Huang1, Shiben Li1, Xinghua Zhang2
1Department of Physics, Wenzhou University, Wenzhou, Zhejiang 325035, China.
This study introduces an efficient deep neural network model for calculating the polymer chain structure factor. This method provides accurate predictions and is more computationally efficient than traditional approaches for polymer physics research.
Area of Science:
- Polymer Physics
- Computational Materials Science
- Data-Driven Science
Background:
- The structure factor is crucial for understanding polymer chain internal structure.
- Analytical solutions exist for Gaussian chains, but wormlike chains require computationally intensive numerical methods.
- Existing methods for calculating the structure factor are often region-specific and resource-demanding.
Purpose of the Study:
- To develop an efficient and universally applicable model for calculating the polymer chain structure factor.
- To leverage deep neural networks for a more streamlined computational approach.
- To enable accurate prediction of polymer chain properties from scattering data.
Main Methods:
- Training a deep neural network (DNN) to model the structure factor.
- Developing a unified model applicable across different chain rigidities and wave vector regions.
- Utilizing the trained DNN to predict polymer contour and Kuhn lengths from experimental scattering data.
Main Results:
- An efficient DNN model was developed for calculating the polymer chain structure factor.
- The model eliminates the need for region-specific calculations based on chain rigidity or wave vector.
- The DNN model demonstrated reasonable accuracy in predicting polymer contour and Kuhn lengths from experimental data.
Conclusions:
- The developed DNN model offers a computationally efficient and accurate alternative for structure factor calculations in polymer physics.
- This approach simplifies the analysis of polymer chain structure compared to traditional numerical methods.
- The study presents a promising method for experimental determination of polymer chain parameters like contour and Kuhn lengths.

