Applying the Monte Carlo technique to build up models of glass transition temperatures of diverse polymers

Toropov, Andrey A.; Toropova, Alla P.; Kudyshkin, V. O.; Bozorov, N. I.; Рашидова, С. Ш.

doi:10.1007/s11224-020-01588-8

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with accurate predictions for a highly diverse set of 133 organic polymers [35]. Numerous works reported attempts to predict polymer properties such as glass transition temperature, T g using QSPR [29,36,37,38,39]. The knowledge of T g defines domains of rigid structure or rubber-like properties for polymeric materials, and thus is of utmost importance for many appli-cations.…”

Section: Introductionmentioning

confidence: 99%

Fuel sorption into polymers: Experimental and machine learning studies

Creton

Veyrat

Klopffer

2022

Fluid Phase Equilibria

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Fuel sorption into polymers: Experimental and machine learning studies

Creton

Veyrat

Klopffer

2022

Fluid Phase Equilibria

View full text Add to dashboard Cite

“…Quantitative structure–property relationship (QSPR) models have been successfully used for understanding, designing, and predicting material properties − (glass transition temperature, boiling point, or partition coefficients, among many others). They are based on the premise that the chemical structure of materials is largely related to their properties, and therefore, materials with chemically similar structures will have similar observed properties.…”

Section: Introductionmentioning

confidence: 99%

Mapping Chemical Structure–Glass Transition Temperature Relationship through Artificial Intelligence

Miccio

Schwartz

2021

Macromolecules

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have been successfully used in the past to predict different properties of polymers based on their chemical structure and to localize and quantify the intramonomer contributions to these properties. In this work, we propose to move forward in order to use the mathematical framework of the ANN for embedding the chemical structure of monomers into a high-dimensional abstract space. This approach allows us not only to accurately predict the glass transition temperature (T g) of polymers but, even more important, also to encode their chemical structure as m-dimensional vectors in a mathematical space. For this aim, we employed a fully connected neural network trained with a set of more than 200 atactic acrylates that provide the coordinates of the vectorized chemical structures into the m-dimensional space. These data points were then treated with a hierarchical nonparametric clusterization method in order to automatically group similar chemical structures into clusters with alike properties. These clusters were then projected into a human-readable three-dimensional space using principal component analysis. This approach allows us to deal with chemical structures as if they were mathematical entities and therefore to perform quantitative operations, so far hardly imaginable, being essential for both the design of new materials and the understanding of the structure–property relationships.

show abstract

“…The great advance in the field of polymeric materials, particularly in the relationship between the molecular structure and its properties, led to the incorporation of in silico tests [1][2][3][4][5]. They are virtual tests, carried out to know the polymeric material properties in the early stages of design, before being synthesized [6][7][8].…”

mentioning

confidence: 99%