AI Application in Material Science and Engineering

This course offers an applied introduction to artificial intelligence (AI) with a special focus on material science and engineering. Learners begin by exploring how metallic materials behave, degrade, and are maintained — and then progress into the foundations of data science and machine learning that enable modern AI applications.

Approximately one-third of the course introduces core concepts in material science: types of metals, their microstructure and properties, as well as typical degradation mechanisms such as fatigue and corrosion. These examples serve as a real-world entry point to the course and demonstrate where AI methods can make a tangible difference — for instance, in detecting cracks in infrastructure, or predicting corrosion in ship hulls.

Building on this foundation, the remaining two-thirds of the course cover key AI and data science methods. Learners are introduced to supervised and unsupervised learning, neural networks, model evaluation metrics, and the importance of reproducibility in scientific computing. Throughout, participants use Python and common open-source libraries such as Scikit-learn, NumPy, and TensorFlow to implement and test machine learning models.

The course is fully online and self-paced. It is particularly suitable for learners with backgrounds in engineering or natural sciences who wish to gain hands-on experience with AI tools — while seeing their relevance in real-world technical systems such as aerospace, energy, or infrastructure. By the end, learners will not only be able to implement basic AI models, but also critically evaluate their application to practical engineering problems.