MSE59700 - Artificial Intelligence in Semiconductor Microstructure Analysis

This online course introduces the application of artificial intelligence (AI) and data-driven methods to semiconductor microstructure analysis.

Credit Hours: 1

Instructor(s): Mohamad Zbi, Associate Professor of Practice, School of Materials Engineering

Email: mzbib@purdue.edu

Fall 2026 Syllabus


Learning Objective:

  1. Apply AI-based data analysis methods to microscopy images and characterization datasets to identify defects, phases, and microstructural features in semiconductor materials
  2. Evaluate the suitability and limitations of AI models for semiconductor microstructure  analysis, including data quality, model assumptions, and interpretation of results
  3. Use data-driven approaches to relate microstructure to properties, demonstrating how AI tools can support prediction, diagnostics, and decision-making in semiconductor research and manufacturing contexts.

Description:

This online course introduces the application of artificial intelligence (AI) and data-driven methods to semiconductor microstructure analysis. Students explore how microscopy images and characterization datasets are analyzed using machine learning techniques for defect detection, phase identification, and microstructure-property relationships in semiconductor materials. Emphasis is placed on practical workflows, model selection, data quality, and interpretation of results in both research and industrial contexts.


Topics Covered:

Module 1 - Introduction to AI in Semiconductor Characterization

Module 2 - AI for Microscopy Image Analysis

Module 3 - AI Models and Data Interpretation

Module 4 - Microstructure-Property Relationships and Predictive AI

Module 5 - Industrial Applications and Future Directions of AI in Semiconductor Characterization


Applied / Theory:

100%/0%


Web Address:

https://purdue.brightspace.com


Homework:

5 Assignments


Projects:

No project


Exams:

5 Quizzes


Textbooks:.

There is no textbook required for this course. All supporting materials will be provided through the Brightspace system. These resources will be organized by module and include links to journal articles, websites, etc.