AI-Powered Innovation in Materials Science

The Role of Language Models in Discovery and Design
1. Auflage 2026
ISBN: 978-3-527-35635-5
Verlag: WILEY-VCH

Buch, Englisch, 576 Seiten, Format (B × H): 170 mm x 244 mm, Gewicht: 680 g

This book offers a groundbreaking exploration of how language models and machine learning are revolutionizing every stage of materials research?from data mining and predictive modeling to autonomous experimentation and AI-driven discovery. Addressing a critical gap at the intersection of artificial intelligence and materials science, this book provides a comprehensive resource that combines foundational theory with practical applications. In addition, it offers timely expertise, actionable insights, interdisciplinary appeal, and accelerated innovation. This book serves as an essential reference for academia and industry, enabling faster, smarter materials development to tackle grand challenges in energy, sustainability, and advanced manufacturing.

Autoren/Hrsg.

Jiang, Xue

Su, Yanjing

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Naturwissenschaften Chemie Analytische Chemie Instrumentelle Analytik, Chromatographie
• Technische Wissenschaften Maschinenbau | Werkstoffkunde Technische Mechanik | Werkstoffkunde Werkstoffkunde, Materialwissenschaft: Forschungsmethoden

Inhaltsverzeichnis

Preface xi

1 The Revolution of AI for Materials 1

2 Fundamentals of Language Models and NLP 37

3 Reinforcement Learning in Materials 89

4 Materials Word Embedding Models 135

5 Materials Transformer-based Models 157

6 Materials Data Extraction from Literature by NLP and Large Language Models 205

7 Case Studies of Chemical Information Extraction 219

8 Case Studies of Alloy Information Extraction 243

9 Case Studies of Materials Synthesis Information Extraction 299

10 Materials Predictive Modeling with Language-augmented Approaches 317

11 Case Studies of Materials Predictive Modeling 339

12 Retrieval-augmented Generation for Materials Large Language Models 387

13 Fine-tuning and Application for Materials Large Language Models 419

14 Materials Agents for Autonomous Research 449

15 Case Studies of Materials Agents 505

16 Challenges and Future Developments 551

Index 559

Chapter 1: The Revolution of AI for Materials
Chapter 2: Fundamentals of Language Models and NLP
Chapter 3: Reinforcement Learning in Materials
Chapter 4: Large Language Models for Materials
Chapter 5: Materials Data Extraction from Literature by NLP and Large Language Models
Chapter 6: Predictive Modeling with Language-Augmented Approaches
Chapter 7: Chapter 7 Conversational Large Language Models for Materials Research
Chapter 8: Materials Agents for Autonomous Research
Chapter 9: Challenges and Future Developments
 

Über Autor(innen)

Xue Jiang is an Associate Professor at the University of Science and Technology Beijing, specializing in materials big data and intelligent materials R&D. She has led 6 competitive research projects, including the National Natural Science Foundation of China (NSFC) Young Scientists Fund, Guangdong Basic and Applied Basic Research Foundation, and key topics under Guangdong Provincial Key R&D Program. Additionally, she has contributed to 14 major national initiatives, such as the National Key R&D Program of China and NSFC Joint Key Projects. With 30 first/corresponding-author publications in top-tier journals (e.g., Acta Materialia, npj Computational Materials, Scripta Materialia), her work includes 25 SCI-indexed papers (12 in TOP journals) and 1 ESI Highly Cited Paper. She holds 22 authorized invention patents and software copyrights. An active educator, Dr. Jiang co-developed the "Materials Genome Engineering" curriculum series, teaching courses like Fundamentals of Materials Design, Materials Data Science, and Materials Big Data Technology. She has co-authored 3 academic books. As a core member of the National Advanced Materials Big Data Center and recipient of the 2023 Materials Genome Engineering Young Scientist Award, she serves on the CSTM Committee for Materials Genome Engineering and as a Youth Editorial Board Member of MGE Advances. She also reviews for prestigious journals (Nature Synthesis, npj Computational Materials, etc.).
 
Yanjing Su is a distinguished scholar and leading expert at the University of Science and Technology Beijing in materials big data, artificial intelligence, and corrosion science. With extensive expertise spanning fundamental research and industrial applications, he has made seminal contributions to the development of data-driven materials science and next-generation corrosion-resistant alloys. As a key advisor to China's national scientific initiatives, he serves on multiple high-level expert committees, including the Ministry of Industry and Information Technology's "Materials Genome Engineering Key Technologies" program, the National Key R&D Program on "Rare Earth New Materials," and the NSFC's major research plan on explainable AI technologies. His work has resulted in over 300 publications in top-tier journals including Acta Materialia, Corrosion Science, and npj Computational Materials, along with 4 influential academic monographs. His achievements have been recognized with numerous honors, including the National First Prize for Educational Achievement (China's highest teaching award) and six provincial/ministerial awards for scientific and technological progress. The integrated Materials Genome Engineering Platform he developed, combining databases, data acquisition, and machine learning tools, has become a valuable resource for both academic research and industrial R&D.