Introduction to Data Science in Materials Science and Engineering

Example how machine learning and large language models can be used to predict cell behaviour in response to biomaterials. Taken and adapted under a CC-BY-4.0 license from Helmholz et al., Computational and Structural Biotechnology Journal(2025). https://doi.org/10.1016/j.csbj.2025.06.023

Unlock the power of data! This lecture takes you on an exciting journey through the core methods that drive modern materials research. From mathematical foundations to neural networks, unsupervised learning, and dimensionality reduction, you’ll explore essential tools such as regression methods, optimization techniques, decision trees, random forests, support vector machines, and more.

By the end of the course, you will
✨ understand fundamental methods in data science,
✨ know how to apply them to real scientific questions in materials science and engineering,
✨ be able to judge which methods fit which tasks,
✨ implement all techniques hands-on in Python, and
✨ confidently interpret and evaluate your results.

Join us and discover how data-driven approaches are shaping the future of materials science! 

Learning goals

  • The students will be able to explain fundamental methods in data science and have practised applying these to scientific questions in materials science and engineering.
  • The students are able to assess the suitability of different methods for a given task and compare these.
  • The students are capable to implement the methods in Python for a given question and can interpret the results.

Lecture content

  1. Mathematical foundations
  2. Linear and polynomial regression
  3. Optimization and error metrics
  4. Logistic regression
  5. k-nearest neighbours
  6. Decision trees and random forests
  7. Support vector machines
  8. Neural networks
  9. Unsupervised methods
  10. Dimensionality reduction
  11. Design of experiment
  12. Outlook into deep learning

Comments

  • The exam is an oral exam including a presentation and the submission of a written report
  • The lecture is given in English
  • Recommended prior knowledge is „Mathematik für Ingenieure 1-3“ and „Einführung in die Programmierung“