Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm

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

---

Rationally Designed High-Temperature Polymer Dielectrics for Capacitive Energy Storage: An Experimental and Computational Alliance

Progress in Polymer Science, Journal Year: 2025, Volume and Issue: unknown, P. 101931 - 101931

Published: Feb. 1, 2025

Language: Английский

---

A Rapid UV/Vis Assisted Designing of Benzodithiophene Based Polymers by Machine Learning to Predict Their Light Absorption for Photovoltaics

Organic Electronics, Journal Year: 2025, Volume and Issue: unknown, P. 107227 - 107227

Published: Feb. 1, 2025

Language: Английский

---

A Graph Neural Network Assisted Reverse Polymers Engineering to Design Low Bandgap Benzothiophene Polymers for Light Harvesting Applications

Materials Chemistry and Physics, Journal Year: 2025, Volume and Issue: unknown, P. 130747 - 130747

Published: March 1, 2025

Language: Английский

---

Bone-brain interaction: mechanisms and potential intervention strategies of biomaterials

Bone Research, Journal Year: 2025, Volume and Issue: 13(1)

Published: March 17, 2025

Abstract Following the discovery of bone as an endocrine organ with systemic influence, bone-brain interaction has emerged a research hotspot, unveiling complex bidirectional communication between and brain. Studies indicate that brain can influence each other’s homeostasis via multiple pathways, yet there is dearth systematic reviews in this area. This review comprehensively examines interactions across three key areas: bone-derived factors on function, effects brain-related diseases or injuries (BRDI) health, concept skeletal interoception. Additionally, discusses innovative approaches biomaterial design inspired by mechanisms, aiming to facilitate through materiobiological aid treatment neurodegenerative bone-related diseases. Notably, integration artificial intelligence (AI) highlighted, showcasing AI’s role expediting formulation effective targeted strategies. In conclusion, offers vital insights into mechanisms suggests advanced harness these clinical practice. These offer promising avenues for preventing treating impacting skeleton brain, underscoring potential interdisciplinary enhancing human health.

Language: Английский

---

Applications of Artificial Intelligence and Machine Learning on Critical Materials Used in Cosmetics and Personal Care Formulation Design

Current Opinion in Colloid & Interface Science, Journal Year: 2024, Volume and Issue: 73, P. 101847 - 101847

Published: Aug. 3, 2024

Language: Английский

---

Discovering polyimides and their composites with targeted mechanical properties through explainable machine learning

Journal of Materials Informatics, Journal Year: 2025, Volume and Issue: 5(1)

Published: Jan. 4, 2025

Polyimides (PIs) are widely used in industries for their exceptional mechanical properties and thermal resilience. Despite benefits, the traditional development process PIs is time-consuming, often lagging behind increasing demand materials with tailored properties. In this study, we introduce a machine learning-based approach to predict optimize of PI composites. We developed six predictive models assess structures under various conditions, aiming enhance our understanding behavior facilitate discovery high-performance structures. By analyzing substructures within top-performing PIs, identified key structural motifs that contribute improved tensile strength, modulus, elongation at break. Furthermore, examined influence fillers on composites, revealing rigid such as SiO2 graphene oxide (GO) significantly improve properties, GO showing versatile enhancement across multiple then screened 800,000 virtual by using models, identifying several candidates targeted These findings provide basis future experimental validation optimal fillers, offering an efficient pathway accelerate design Our study can also be extended other research, serving valuable paradigm polymers

Language: Английский

---

Machine‐Learning‐Enhanced Trial‐and‐Error for Efficient Optimization of Rubber Composites

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

Published: March 10, 2025

The traditional trial-and-error approach, although effective, is inefficient for optimizing rubber composites. latest developments in machine learning (ML)-assisted methodologies are also not suitable predicting and composite properties. This due to the dependency of properties on processing conditions, which prevents alignment data collected from different sources. In this work, a novel workflow called ML-enhanced approach proposed. integrates orthogonal experimental design with symbolic regression (SR) effectively extract empirical principles. combination enables optimization process retain characteristics while significantly improving efficiency capability. Using composites as model system, extracts principles encapsulated by high-frequency terms SR-derived mathematical formulas, offering clear guidance material property optimization. An online platform has been developed that allows no-code usage proposed methodology, designed seamlessly integrate into existing process.

Language: Английский

---

Tailoring polymer architectures to drive molecular sieving in protein-polymer hybrids

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

Published: March 14, 2025

Language: Английский

---

Machine learning approaches for designing polybenzoxazines with balanced thermal stability and dielectric properties

Science China Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Language: Английский

---