Home Physical Sciences Chapter 7 Predicting polymer properties: machine learning insights from Polymer Genome
Chapter
Licensed
Unlicensed Requires Authentication

Chapter 7 Predicting polymer properties: machine learning insights from Polymer Genome

  • Ruby Srivastava ORCID logo
Become an author with De Gruyter Brill
Explore this Subject How to publish with us
Artificial Intelligence in Polymer Science and Nanotechnology
This chapter is in the book Artificial Intelligence in Polymer Science and Nanotechnology

Abstract

Data-driven and machine learning (MLmachine learning)-based approaches have recently been employed in materials science to enable rapid predictions of material properties. Polymers, known for their affordability and highly customizable properties, are widely utilized in various technological applications. However, their complex chemical composition and morphology present challenges in their development. The fusion of ML algorithms with vast data resources has opened new avenues for progress in polymer science and engineering. Polymer informaticsinformatics has emerged as a field aimed at accelerating the performance and optimization of process for novel polymerspolymers through MLmachine learning models trained on reliable data, as these materials exhibit unique physical behaviors across vast length-time scales, particularly in nonequilibrium glassy states, where experimental depictions and simulations are expensive and challenging. With the continuous growth of existing databases, the emergence of new data resources, and ongoing advancements in MLmachine learning algorithms, the landscape of informatics in polymers is becoming increasingly systematic and broadly applicable. One notable development in this field is Polymer GenomePolymer Genome, an informatics program, aimed to predict various critical desired polymer properties. This platform, trained on a large polymer dataset, employs surrogate MLmachine learning models that correlate key polymer features with their properties, leveraging high-throughput density functional theorydensity functional theory (DFT)) alongside experimental data sources from literature and established databases. Despite its robustness and predictive power, these models still face limitations in designing materials that meet specific property or performance objectives.

Abstract

Data-driven and machine learning (MLmachine learning)-based approaches have recently been employed in materials science to enable rapid predictions of material properties. Polymers, known for their affordability and highly customizable properties, are widely utilized in various technological applications. However, their complex chemical composition and morphology present challenges in their development. The fusion of ML algorithms with vast data resources has opened new avenues for progress in polymer science and engineering. Polymer informaticsinformatics has emerged as a field aimed at accelerating the performance and optimization of process for novel polymerspolymers through MLmachine learning models trained on reliable data, as these materials exhibit unique physical behaviors across vast length-time scales, particularly in nonequilibrium glassy states, where experimental depictions and simulations are expensive and challenging. With the continuous growth of existing databases, the emergence of new data resources, and ongoing advancements in MLmachine learning algorithms, the landscape of informatics in polymers is becoming increasingly systematic and broadly applicable. One notable development in this field is Polymer GenomePolymer Genome, an informatics program, aimed to predict various critical desired polymer properties. This platform, trained on a large polymer dataset, employs surrogate MLmachine learning models that correlate key polymer features with their properties, leveraging high-throughput density functional theorydensity functional theory (DFT)) alongside experimental data sources from literature and established databases. Despite its robustness and predictive power, these models still face limitations in designing materials that meet specific property or performance objectives.

Chapters in this book

  1. Frontmatter I
  2. Preface V
  3. Foreword VII
  4. Contents IX
  5. List of contributing authors XIII
  6. Chapter 1 Nanotechnology innovation: AI-enhanced polymer drug delivery systems 1
  7. Chapter 2 Machine learning applications in material science: unveiling innovative solutions 27
  8. Chapter 3 Machine learning for material simulation: revolutionizing polymer science 55
  9. Chapter 4 The autonomous revolution: role of AI in self-driving labs for materials sciences 69
  10. Chapter 5 AI-powered polymer sequence design: applications and innovations 97
  11. Chapter 6 Exploring the relationship between structure and properties in polymer blends using deep learning techniques 127
  12. Chapter 7 Predicting polymer properties: machine learning insights from Polymer Genome 159
  13. Chapter 8 AI-driven development: innovating biomedical polymer materials 175
  14. Chapter 9 Predictive precision: AI-enhanced measurement of mechanical properties in nanostructured polymer composites 203
  15. Chapter 10 Artificial intelligence in polymer molding and extrusion 255
  16. Chapter 11 Discovering new frontiers: material explorations with AI and polymers 281
  17. Chapter 12 Advancing nanomaterial safety: AI in toxicity and environmental assessments 299
  18. Chapter 13 Innovative approaches in drug delivery systems (DDS) leveraging AI and advanced material characterization 331
  19. Chapter 14 Robotics innovations in nanotechnology: redefining polymer science with AI 369
  20. Editor’s biography
  21. Index 403
https://doi.org/10.1515/9783111681870-007

Chapters in this book

  1. Frontmatter I
  2. Preface V
  3. Foreword VII
  4. Contents IX
  5. List of contributing authors XIII
  6. Chapter 1 Nanotechnology innovation: AI-enhanced polymer drug delivery systems 1
  7. Chapter 2 Machine learning applications in material science: unveiling innovative solutions 27
  8. Chapter 3 Machine learning for material simulation: revolutionizing polymer science 55
  9. Chapter 4 The autonomous revolution: role of AI in self-driving labs for materials sciences 69
  10. Chapter 5 AI-powered polymer sequence design: applications and innovations 97
  11. Chapter 6 Exploring the relationship between structure and properties in polymer blends using deep learning techniques 127
  12. Chapter 7 Predicting polymer properties: machine learning insights from Polymer Genome 159
  13. Chapter 8 AI-driven development: innovating biomedical polymer materials 175
  14. Chapter 9 Predictive precision: AI-enhanced measurement of mechanical properties in nanostructured polymer composites 203
  15. Chapter 10 Artificial intelligence in polymer molding and extrusion 255
  16. Chapter 11 Discovering new frontiers: material explorations with AI and polymers 281
  17. Chapter 12 Advancing nanomaterial safety: AI in toxicity and environmental assessments 299
  18. Chapter 13 Innovative approaches in drug delivery systems (DDS) leveraging AI and advanced material characterization 331
  19. Chapter 14 Robotics innovations in nanotechnology: redefining polymer science with AI 369
  20. Editor’s biography
  21. Index 403
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 6.12.2025 from https://www.degruyterbrill.com/document/doi/10.1515/9783111681870-007/pdf
Scroll to top button