AI and Robotic Technology in Materials and Chemistry Research

Xi Zhu, PhD, is the Deputy Director in the Shenzhen Institute of Artificial Intelligence and Robotics for Society at the Chinese University of Hong Kong. His research is focused on the application of condensed matter physics theory in interdisciplinary research and AI applications in materials science and pharmacy.

• Preface ixAbout the Author xiAcknowledgments xiii1 Survey of Challenges in Chemistry and Materials Science Research 11.1 Introduction 11.2 Energy Form 21.2.1 Steam Power 21.2.2 Electricity Power 41.2.3 Other Energy Forms 81.3 Data 11References 192 Robots Technology Development in Modern Scientific Research 212.1 Introduction 212.2 Early Development of Laboratory Automation (Before 2000) 222.2.1 Early Automation Technologies 222.2.2 Laying the Foundation for AI and Robotics 292.3 Preliminary Integration and Development of Laboratory Automation (2000–2019) 312.3.1 Automation Technologies (2000–2010) 312.3.2 Various Forms of Exploration Based on Established Foundations 412.4 Latest Developments and Current Trends (2020–2023) 422.4.1 Automation Technologies in Five Years 422.4.2 Mature Industrialization as well as In-depth Exploration 502.5 Outlook on Future Development 522.6 Conclusion 54References 553 AI Algorithm for Chemical and Bio-material Design 573.1 Introduction 573.2 Molecular Representation and Encoding 583.2.1 Linear Notations for Molecules 583.2.2 Graph Representations for Molecules 633.3 The Formulation of Accessible and Searchable Data 663.3.1 Traditional Way for Molecular Structure–Property Relationship Determination: The Kohn–Sham Equation 663.3.2 Dataset Preprocessing 683.3.3 Current Existing Dataset 693.4 AI for Molecular Structure–Property Relationship 713.4.1 The Deep Learning Technology 723.4.2 AI Solving the Kohn–Sham Equation 753.5 AI for Chemical and Bio-material Design 783.5.1 Design Workflows 783.5.2 Example of Designed Chemical and Bio-materials 79References 814 Autonomous Laboratory Empowered by AI and Robotics 854.1 Evolution of Laboratory 854.2 Core Technologies in Autonomous Laboratories 854.2.1 Autonomous Laboratory Components 854.2.2 Reinforcement Learning 894.3 Example Autonomous Laboratory Solution 904.3.1 Automatic Device only Solution 904.3.2 Solution that Including Design and React 914.3.3 Solution in Reaction Optimization 924.3.4 Solutions Contain Full Phases 944.4 Advanced Autonomous Laboratory Solutions 984.4.1 Advanced Experimental Data Analysis Methods 984.4.2 Design and Analysis in the Large Model Era 1044.4.3 Experiment Visualization 1064.5 Future Prospects and Trends 108References 1105 Large Language Models for the Autonomous Material Research 1135.1 Review of Large Language Models Development and Applications 1135.2 Fundamentals of LLM for Material Research: Database and Knowledge Base Construction 1215.3 Evaluation: Spider Matrix 1245.4 Ideation: AI Supervisor and ScholarNet 1305.5 Results and Discussion 1345.6 Conclusion 136References 1366 Toward a Blockchain-Powered Anti-Counterfeiting Experimental Data System in an Autonomous Laboratory 1396.1 Blockchain Technology 1396.2 Laboratory Chemical Management and Safety 1436.3 The Problem of Data Integrity and Counterfeiting in Scientific Research 1456.4 Blockchain in the Autonomous Laboratory 1506.5 Symbolic Representation of Experiments 1556.6 Challenges and Limitations 1576.6.1 Standard Compilation for Experiment Methods 1576.6.2 High Cost for PoW and PoS 1586.6.2.1 Data Storage Safety 1586.7 Conclusion 159References 1607 The Future Integrated Computational and Experimental Research in Metaverse 1637.1 Introduction of Metaverse 1637.1.1 Industry 5.0 Protocol 1637.1.2 Current Development of Metaverse 1647.1.3 Human-in-Loop Paradigm 1657.2 Research Paradigm in Metaverse 1657.3 Autonomous High-Throughput Experiments 1667.3.1 Theory Driven by AI 1687.3.2 HIL Implementation 1697.3.3 AI Prediction 1717.4 H2O Phase Research in Metaverse 1727.5 Aqueous System Research in Metaverse 1767.6 Challenges and Future Directions 182References 182Index 187