Machine Learning‐Driven Discovery of Thermoset Shape Memory Polymers With High Glass Transition Temperature Using Variational Autoencoders DOI
Amir Teimouri, Guoqiang Li

Journal of Polymer Science, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 25, 2024

ABSTRACT The discovery of high‐performance shape memory polymers (SMPs) with enhanced glass transition temperatures (Tg) is paramount importance in fields such as geothermal energy, oil and gas, aerospace, other high‐temperature applications, where materials are required to exhibit effect at extremely conditions. Here, we employ a novel machine learning framework that integrates transfer variational autoencoders (VAE) efficiently explore the chemical design space SMPs identify new candidates high Tg values. We systematically investigate different latent dimensions on VAE model performance. Several models then trained predict Tg. find SVM demonstrates highest predictive accuracy, R 2 values exceeding 0.87 mean absolute percentage error low 6.43% test set. Through systematic molar ratio adjustments VAE‐based fingerprinting, discover SMP between 190°C 200°C, suitable for applications. These findings underscore effectiveness combining VAEs discovery, offering scalable efficient method identifying tailored thermal properties.

Language: Английский

Machine Learning in Polymer Research DOI Creative Commons

Wei Ge,

R. Silva‐González, Yanan Fan

et al.

Advanced Materials, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 9, 2025

Machine learning is increasingly being applied in polymer chemistry to link chemical structures macroscopic properties of polymers and identify patterns the that help improve specific properties. To facilitate this, a dataset needs be translated into machine readable descriptors. However, limited inadequately curated datasets, broad molecular weight distributions, irregular configurations pose significant challenges. Most off shelf mathematical models often need refinement for applications. Addressing these challenges demand close collaboration between chemists mathematicians as must formulate research questions terms while are required refine This review unites both disciplines address curation hurdles highlight advances synthesis modeling enhance data availability. It then surveys ML approaches used predict solid-state properties, solution behavior, composite performance, emerging applications such drug delivery polymer-biology interface. A perspective field concluded importance FAIR (findability, accessibility, interoperability, reusability) integration theory discussed, thoughts on machine-human interface shared.

Language: Английский

Citations

2
Advances in natural fiber polymer and PLA composites through artificial intelligence and machine learning integration DOI Creative Commons

Md. Helal Uddin,

Mohammed Huzaifa Mulla,

Tarek Abedin

et al.

Journal of Polymer Research, Journal Year: 2025, Volume and Issue: 32(3)

Published: Feb. 24, 2025

Language: Английский

Citations

2
Machine Learning-Aided Inverse Design and Discovery of Novel Polymeric Materials for Membrane Separation DOI Creative Commons

Raghav Dangayach,

Nohyeong Jeong, Elif Demirel

et al.

Environmental Science & Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 16, 2024

Polymeric membranes have been widely used for liquid and gas separation in various industrial applications over the past few decades because of their exceptional versatility high tunability. Traditional trial-and-error methods material synthesis are inadequate to meet growing demands high-performance membranes. Machine learning (ML) has demonstrated huge potential accelerate design discovery membrane materials. In this review, we cover strengths weaknesses traditional methods, followed by a discussion on emergence ML developing advanced polymeric We describe methodologies data collection, preparation, commonly models, explainable artificial intelligence (XAI) tools implemented research. Furthermore, explain experimental computational validation steps verify results provided these models. Subsequently, showcase successful case studies emphasize inverse methodology within ML-driven structured framework. Finally, conclude highlighting recent progress, challenges, future research directions advance next generation With aim provide comprehensive guideline researchers, scientists, engineers assisting implementation process.

Language: Английский

Citations

6
Self-assembly of architected macromolecules: Bridging a gap between experiments and simulations DOI Open Access
Ji Woong Yu, Changsu Yoo, Suchan Cho

et al.

Chemical Physics Reviews, Journal Year: 2025, Volume and Issue: 6(1)

Published: Jan. 27, 2025

Macromolecular self-assembly is essential in life and interfacial science. A macromolecule consisting of chemically distinct components tends to self-assemble a selective solvent minimize the exposure solvophobic segments medium while solvophilic adopt extended conformations. While micelles composed linear block copolymers represent classic examples such solution assembly, recent interest focuses on complex macromolecules with nonlinear architectures, as star, graft, bottlebrush. Such include several hundreds polymer chains covalently tied core backbone. The pre-programmed, non-exchangeable chain arrangement makes huge difference their self-assembly. field has witnessed tremendous advances synthetic methodologies construct desired leading discoveries exotic behavior. Thanks rapid evolution computing power, computer simulation also been an emerging complementary approach for understanding association mechanism further predicting self-assembling morphologies. However, simulating architected posed challenge number objects should be included simulations. Comparing experimental results simulations not always straightforward, routes well-defined model systems systematically controlled structural parameters are often available. In this manuscript, we propose bridge gap between experiments macromolecules. We focus key articles area reporting evidence details cover literature. start discussing applicable investigate across multiple levels chemical resolution from all-atom particle dynamics. Then, delve into topological design, synthesis, macromolecules, including dendritic/star, network, graft/bottlebrush polymers, understand architectural effect expand our discourse embrace toward realizing more systems. For example, presence strong Coulombic interactions, case polyelectrolytes, geometric constraints, other solutions, exemplified by inorganic fillers, introduced. Finally, challenges perspectives discussed final section manuscript.

Language: Английский

Citations

0
Ten Problems in Polymer Reactivity Prediction DOI
Nicholas E. Jackson, Brett M. Savoie

Macromolecules, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

Language: Английский

Citations

0
Tailoring polymer architectures to drive molecular sieving in protein-polymer hybrids DOI Creative Commons
Kriti Kapil, Hironobu Murata, Lucca Trachsel

et al.

Sustainable Chemistry and Pharmacy, Journal Year: 2025, Volume and Issue: 45, P. 101988 - 101988

Published: March 14, 2025

Language: Английский

Citations

0
Structural flexibility and mobility of coordination polymers on Cu(111) DOI Creative Commons
Waka Nakanishi, Masayuki Takeuchi, Keisuke Sagisaka

et al.

Chemical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Reduction of ligand–surface interactions facilitated motion coordination polymers on Cu(111). STM observations over a range temperatures revealed structure-dependent vibrational behavior and chain modifications at the single-molecule level.

Language: Английский

Citations

0
Leveraging generative models with periodicity-aware, invertible and invariant representations for crystalline materials design DOI
Zhilong Wang, Fengqi You

Nature Computational Science, Journal Year: 2025, Volume and Issue: unknown

Published: May 9, 2025

Language: Английский

Citations

0
Physics-Guided Neural Networks for Transferable Property Prediction in Architecturally Diverse Copolymers DOI
S Jiang, Michael Webb

Macromolecules, Journal Year: 2025, Volume and Issue: unknown

Published: May 13, 2025

Language: Английский

Citations

0
Machine Learning in 3D and 4D Printing of Polymer Composites: A Review DOI Open Access
Ivan Malashin, Igor Masich, В С Тынченко

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(22), P. 3125 - 3125

Published: Nov. 8, 2024

The emergence of 3D and 4D printing has transformed the field polymer composites, facilitating fabrication complex structures. As these manufacturing techniques continue to progress, integration machine learning (ML) is widely utilized enhance aspects processes. This includes optimizing material properties, refining process parameters, predicting performance outcomes, enabling real-time monitoring. paper aims provide an overview recent applications ML in composites. By highlighting intersection technologies, this seeks identify existing trends challenges, outline future directions.

Language: Английский

Citations

3