Machine Learning in Polymer Science: Emerging Trends and Future Directions DOI
Pradeepta Kumar Sarangi,

Nidhi Goel,

Ashok Kumar Sahoo

et al.

Macromolecular Symposia, Journal Year: 2025, Volume and Issue: 414(1)

Published: Feb. 1, 2025

Abstract Artificial intelligence (AI) and machine learning (ML) have advanced tremendously in the previous 5 years regarding polymer science. Polymers are materials with enormous versatility that now widely used. found extensive applications several fields such as energy storage, construction, medical, aerospace, other industries. This study is presently era of 4.0 industry, a transformative period profoundly reshaping both business society an unprecedented manner specifically developing countries. Data‐driven strategies for process analysis control crucial expediting creation production processes while maintaining product quality avoiding rise cost. More more scientists utilizing informatics data science to create new understand connections between their molecular structure characteristics. The field relatively new. Even though there lot helpful databases tools accessible, not many used frequently. application AI starting influence on aspects human existence, including technology. Polymer utilizes ML techniques enhance developing, designing, discovering polymers. Based these ideas, it examines burgeoning ML‐assisted this research. It also looks at developments polymeric ecosystem talks about upcoming potential problems applications.

Language: Английский

polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics DOI Creative Commons

Christopher Kuenneth,

Rampi Ramprasad

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 11, 2023

Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well significant challenges to identify suitable application-specific candidates. We present complete end-to-end machine-driven polymer informatics pipeline can search this space for candidates at speed and accuracy. This includes fingerprinting capability called polyBERT (inspired by Natural Language Processing concepts), multitask learning approach maps the fingerprints host properties. linguist treats structure polymers language. The outstrips best presently available concepts property prediction based on handcrafted fingerprint schemes in two orders magnitude while preserving accuracy, thus making strong candidate deployment scalable architectures including cloud infrastructures.

Language: Английский

Citations

108

TransPolymer: a Transformer-based language model for polymer property predictions DOI Creative Commons
Changwen Xu, Yuyang Wang, Amir Barati Farimani

et al.

npj Computational Materials, Journal Year: 2023, Volume and Issue: 9(1)

Published: April 22, 2023

Abstract Accurate and efficient prediction of polymer properties is great significance in design. Conventionally, expensive time-consuming experiments or simulations are required to evaluate functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance natural language processing. However, such methods not been investigated sciences. Herein, we report TransPolymer, a Transformer-based model for property prediction. Our proposed tokenizer chemical awareness enables learning representations from sequences. Rigorous on ten benchmarks demonstrate the TransPolymer. Moreover, show that TransPolymer benefits pretraining large unlabeled dataset via Masked Language Modeling. Experimental results further manifest important role modeling We highlight this as promising computational tool promoting rational design understanding structure-property relationships data science view.

Language: Английский

Citations

90

Emerging Trends in Machine Learning: A Polymer Perspective DOI Creative Commons
Tyler B. Martin, Debra J. Audus

ACS Polymers Au, Journal Year: 2023, Volume and Issue: 3(3), P. 239 - 258

Published: Jan. 18, 2023

In the last five years, there has been tremendous growth in machine learning and artificial intelligence as applied to polymer science. Here, we highlight unique challenges presented by polymers how field is addressing them. We focus on emerging trends with an emphasis topics that have received less attention review literature. Finally, provide outlook for field, outline important areas science discuss advances from greater material community.

Language: Английский

Citations

88

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery DOI Creative Commons
Gabriel Bradford, Jeffrey Lopez, Jurģis Ruža

et al.

ACS Central Science, Journal Year: 2023, Volume and Issue: 9(2), P. 206 - 216

Published: Jan. 23, 2023

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high SPEs, we developed a chemistry-informed machine learning model that accurately predicts SPEs. The was trained on SPE data hundreds experimental publications. Our encodes Arrhenius equation, which describes temperature activated processes, into readout layer state-of-the-art message passing neural network has improved accuracy over models do not encode dependence. Chemically informed layers are compatible with deep for other property prediction tasks especially useful where limited training available. Using model, values were predicted several thousand candidate formulations, allowing us identify promising We also generated predictions different anions poly(ethylene oxide) poly(trimethylene carbonate), demonstrating utility our identifying descriptors conductivity.

Language: Английский

Citations

69

Applied machine learning as a driver for polymeric biomaterials design DOI Creative Commons
Samantha M. McDonald,

Emily K. Augustine,

Quinn Lanners

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: Aug. 10, 2023

Abstract Polymers are ubiquitous to almost every aspect of modern society and their use in medical products is similarly pervasive. Despite this, the diversity commercial polymers used medicine stunningly low. Considerable time resources have been extended over years towards development new polymeric biomaterials which address unmet needs left by current generation medical-grade polymers. Machine learning (ML) presents an unprecedented opportunity this field bypass need for trial-and-error synthesis, thus reducing invested into discoveries critical advancing treatments. Current efforts pioneering applied ML polymer design employed combinatorial high throughput experimental data availability concerns. However, lack available standardized characterization parameters relevant medicine, including degradation biocompatibility, represents a nearly insurmountable obstacle ML-aided biomaterials. Herein, we identify gap at intersection biomedical design, highlight works junction more broadly provide outlook on challenges future directions.

Language: Английский

Citations

60

Data-Driven Design of Polymer-Based Biomaterials: High-throughput Simulation, Experimentation, and Machine Learning DOI
Roshan Patel, Michael Webb

ACS Applied Bio Materials, Journal Year: 2023, Volume and Issue: 7(2), P. 510 - 527

Published: Jan. 26, 2023

Polymers, with the capacity to tunably alter properties and response based on manipulation of their chemical characteristics, are attractive components in biomaterials. Nevertheless, potential as functional materials is also inhibited by complexity, which complicates rational or brute-force design realization. In recent years, machine learning has emerged a useful tool for facilitating via efficient modeling structure–property relationships domain interest. this Spotlight, we discuss emergence data-driven polymers that can be deployed biomaterials particular emphasis complex copolymer systems. We outline developments, well our own contributions takeaways, related high-throughput data generation polymer systems, methods surrogate learning, paradigms property optimization design. Throughout discussion, highlight key aspects successful strategies other considerations will relevant future polymer-based target properties.

Language: Английский

Citations

55

Advancing 3D bioprinting through machine learning and artificial intelligence DOI
Srikanthan Ramesh, Akash Deep, Ali Tamayol

et al.

Bioprinting, Journal Year: 2024, Volume and Issue: 38, P. e00331 - e00331

Published: Jan. 28, 2024

Language: Английский

Citations

36

Design of functional and sustainable polymers assisted by artificial intelligence DOI
Tran Doan Huan, Rishi Gurnani,

Chiho Kim

et al.

Nature Reviews Materials, Journal Year: 2024, Volume and Issue: 9(12), P. 866 - 886

Published: Aug. 19, 2024

Language: Английский

Citations

34

Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm DOI Creative Commons
Chunhui Xie, Haoke Qiu, Lu Liu

et al.

SmartMat, Journal Year: 2025, Volume and Issue: 6(1)

Published: Jan. 9, 2025

ABSTRACT Machine learning (ML), material genome, and big data approaches are highly overlapped in their strategies, algorithms, models. They can target various definitions, distributions, correlations of concerned physical parameters given polymer systems, have expanding applications as a new paradigm indispensable to conventional ones. Their inherent advantages building quantitative multivariate largely enhanced the capability scientific understanding discoveries, thus facilitating mechanism exploration, prediction, high‐throughput screening, optimization, rational inverse designs. This article summarizes representative progress recent two decades focusing on design, preparation, application, sustainable development materials based exploration key composition–process–structure–property–performance relationship. The integration both data‐driven insights through ML deepen fundamental discover novel is categorically presented. Despite construction application robust models, strategies algorithms deal with variant tasks science still rapid growth. challenges prospects then We believe that innovation will thrive along approaches, from efficient design applications.

Language: Английский

Citations

7

The Rise of Machine Learning in Polymer Discovery DOI Creative Commons
Cheng Yan, Guoqiang Li

Advanced Intelligent Systems, Journal Year: 2023, Volume and Issue: 5(4)

Published: Jan. 31, 2023

In the recent decades, with rapid development in computing power and algorithms, machine learning (ML) has exhibited its enormous potential new polymer discovery. Herein, history of ML is described basic process accelerated discovery summarized. Next, four steps this are reviewed, that is, dataset selection, fingerprinting, framework, generation. Finally, a couple main challenges for presented outlooks field prospected. It expected review can service as useful tool people who just step into deepen understanding already field.

Language: Английский

Citations

43