A Machine Learning Method for Material Property Prediction: Example Polymer Compatibility

TL;DR

This paper introduces a novel machine learning approach for predicting material properties, demonstrated on polymer compatibility, achieving over 75% accuracy by leveraging molecular structures and blending compositions.

Contribution

The paper presents a new general machine learning method for material property prediction, specifically applied to polymer compatibility, with a focus on data mining and structure-property relationship modeling.

Findings

Achieved at least 75% accuracy on a large polymer dataset.

Successfully modeled the relationship between molecular structure and material properties.

Demonstrated the effectiveness of machine learning in material property prediction.

Abstract

Prediction of material property is a key problem because of its significance to material design and screening. We present a brand-new and general machine learning method for material property prediction. As a representative example, polymer compatibility is chosen to demonstrate the effectiveness of our method. Specifically, we mine data from related literature to build a specific database and give a prediction based on the basic molecular structures of blending polymers and, as auxiliary, the blending composition. Our model obtains at least 75% accuracy on the dataset consisting of thousands of entries. We demonstrate that the relationship between structure and properties can be learned and simulated by machine learning method.