Machine learning discovery of high-temperature polymers.
Lei Tao,Guang Chen,Ying Li +2 more
- 26 Mar 2021
- Vol. 2, Iss: 4, pp 100225-100225
79
TL;DR: More than 65,000 promising candidates with Tg > 200°C are identified, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo).
read more
Abstract: Summary To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature T g , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimental T g values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown T g values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates with T g > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
PolyMetriX: an ecosystem for digital polymer chemistry
Sreekanth Kunchapu,Kevin Maik Jablonka,Sreekanth Kunchapu,Kevin Maik Jablonka +3 more
Abstract: Abstract Digital polymer chemistry leverages computational methods to design and optimize polymer materials. While there have been advances in using machine learning to accelerate the design of polymers, the field is hampered by the lack of standards, which precludes comparability and makes it difficult to build on top of prior work. To address this gap, we introduce PolyMetriX, an open-source Python library designed to facilitate the entire polymer informatics workflow—from obtaining data to training models. PolyMetriX provides curated polymer property datasets, and novel featurization techniques that extract hierarchical structural information at the full polymer, backbone, and sidechain levels. Additionally, it incorporates polymer-specific data splitting strategies to ensure robust model generalization. PolyMetriX enhances the predictive performance of models while improving reproducibility in digital polymer chemistry.
Machine learning for layer-by-layer nanofiltration membrane performance prediction and polymer candidate exploration.
Chen Wang,Li Wang,Hanwei Yu,Allan Seo,Zhining Wang,Saeid Rajabzadeh,Bing-Jie Ni,Hokyong Shon +7 more
TL;DR: This study develops machine learning models for predicting layer-by-layer nanofiltration membrane performance and explores polymer candidates using the Shapley Additive exPlanation method, identifying 23 potential polymers for high-performance membrane fabrication.
Polymer Genome Approach: A New Method for Research and Development of Polymers
Shi Du,Song-qi Zhang,Li-quan Wang,Jia-ping Lin,Lei Du +4 more
TL;DR: This review introduces the polymer genome approach, a method combining computer technology, database technology, and experiments to accelerate polymer research and development, and discusses its applications, challenges, and future directions in establishing structure-property relationships and designing advanced polymers.
Advances in stimuli-responsive polymers for biomedical and environmental applications
Tae Woong Kang,Kinam Park,Moon Suk Kim +2 more
References
•Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
•Book
Reinforcement Learning: An Introduction
Richard S. Sutton,Andrew G. Barto +1 more
- 01 Jan 1988
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Advances in Neural Information Processing Systems 28
Peter A. Flach,Meelis Kull +1 more
- 12 Dec 2015
13.6K
Reinforcement learning: a survey
TL;DR: Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.