Materials Informatics

Übersicht

ABOUT THE COURSE:

With the increasing focus on machine learning and artificial intelligence by industries that operate in the materials domain, and the enhanced digitalization efforts being taken up by several industries, this course will equip students with the necessary machine learning skills that can be applied within the materials domain. The course will not only cover the data science aspects, but also the physics behind materials modelling and computations that generate the datasets used.INTENDED AUDIENCE:

Post graduate and advanced undergraduate students of Metallurgy, Materials Science and Engineering, and Ceramic Engineering disciplinesPREREQUISITES:

Students of any metallurgy, materials or related disciplines are welcome.

Lehrplan

• Introduction to Materials Informatics
Overview of materials informatics
Importance of AI and machine learning in materials science
Course objectives and outcomes
• Fundamentals of Machine Learning
Supervised learning: Regression and classification
Unsupervised learning: Clustering and dimensionality reduction
Evaluation metrics and model selection
• Data Science for Materials
Data collection and preprocessing specific to materials
Feature engineering in material datasets
Handling missing and noisy data
• Materials Modelling and Simulations
Basics of materials physics and computational modelling
Types of materials simulations: Molecular dynamics, DFT, etc.
Generating and interpreting simulation data
• Machine Learning Applications in Materials Science
Property prediction and materials discovery
Process optimization and materials design
Case studies and real-world applications
• Advanced Topics in Materials Informatics
Deep learning approaches in materials informatics
AI-driven materials self-healing and adaptability
Integration of materials informatics into industrial pipelines
• Tools and Software in Materials Informatics
Introduction to popular programming languages (Python, R)
Overview of software and tools (MATLAB, TensorFlow, etc.)
Data visualization and reporting in materials informatics
• Project Work
Formulation of research questions
Data analysis and model development
Presentation and peer review
• Future Directions and Emerging Trends
The role of AI in sustainable materials
Ethical considerations in AI-driven materials research
Emerging research areas and technologies
• Course Summary and Review
Recap of key concepts and skills
Discussion of potential career paths in materials informatics
Final Q&A session and feedback collection

---

Unterrichtet von

Prof.Sai Gautam Gopalakrishnan

---

Fachgebiete

Data Science