Machine Learning and Simulation Approaches in Materials Science and EngineeringModule description #31221 / Version 1
- 6 CP
- Written exam
- Graded
- Winter semester
- English
| Module / Version | #31221 / #1 |
|---|---|
| Validity | Since Winter semester 2026/27 |
| Available language(s) | German |
| Credit points | 6 |
| Person responsible for the module | Haase, Christian |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät III |
|---|---|
| Institute | Institut für Werkstoffwissenschaften und -technologien |
| Academic chair | 33341700 FG Materials for Additive Manufacturing |
Contact
| Office | BH-A3 |
|---|---|
| Contact person | Haase, Christian |
| E-mail address | christian.haase@tu-berlin.de |
| Website | https://www.tu.berlin/mfam |
Learning outcomes
In the module “Simulation and machine learning approaches in material science” a comprehensive introduction to the fundamental computational methods used in materials science will be provided, with a focus on physics-based simulations and machine learning. Students will develop a holistic understanding of how various computational techniques are employed to explore new materials, simulate/predict their behavior and properties, and design materials at different, e.g., from atomic to macroscopic, levels.
The course conveys:
40% Knowledge and Understanding
40% Analysis and Methodology
10% Application and Practice
10% Social Competence
The course conveys:
40% Knowledge and Understanding
40% Analysis and Methodology
10% Application and Practice
10% Social Competence
Content
• Understand the fundamental principles and applications of the most important computational techniques to evaluate material behavior including:
- density functional theory (DFT): Å-nm scale
- molecular dynamics (MD): nm - µm scale
- kinetic Monte Carlo (KMC): nm-μm scale
- phase field: nm-mm scale
- cellular automata (CA): μm-mm scale
- finite element method (FEM): mm-m scale
- calculation of phase diagrams (CALPHAD): integrates all scales
- diffusion models: µm-cm scale
- crystal plasticity models: µm-mm scale
• Identify the appropriate simulation approach for a given physical property, microstructural phenomenon, or materials problem across multiple length and time scales.
• Comprehend the interplay between structure, processing, and properties using materials simulations.
• Understand the fundamentals of different machine learning algorithms, including both supervised and unsupervised learning approaches. Regression vs. classification in materials science problems.
• Learn the full workflow of a machine learning project, from training, validation, and testing to hyperparameter tuning, feature engineering, and evaluating model performance.
• Explore the applications of machine learning in materials science, including predicting material properties, designing new chemical compositions, and optimizing processes parameters.
• Critically evaluate the capabilities, limitations, and integration potential of various computational and ML approaches in modern materials research.
- density functional theory (DFT): Å-nm scale
- molecular dynamics (MD): nm - µm scale
- kinetic Monte Carlo (KMC): nm-μm scale
- phase field: nm-mm scale
- cellular automata (CA): μm-mm scale
- finite element method (FEM): mm-m scale
- calculation of phase diagrams (CALPHAD): integrates all scales
- diffusion models: µm-cm scale
- crystal plasticity models: µm-mm scale
• Identify the appropriate simulation approach for a given physical property, microstructural phenomenon, or materials problem across multiple length and time scales.
• Comprehend the interplay between structure, processing, and properties using materials simulations.
• Understand the fundamentals of different machine learning algorithms, including both supervised and unsupervised learning approaches. Regression vs. classification in materials science problems.
• Learn the full workflow of a machine learning project, from training, validation, and testing to hyperparameter tuning, feature engineering, and evaluating model performance.
• Explore the applications of machine learning in materials science, including predicting material properties, designing new chemical compositions, and optimizing processes parameters.
• Critically evaluate the capabilities, limitations, and integration potential of various computational and ML approaches in modern materials research.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Machine Learning and Simulation Approaches in Materials Science and Engineering | Integrated course | 3417 L 003 | Winter semester | [en] | 6 | ISIS |
Workload and credit points
Machine Learning and Simulation Approaches in Materials Science and Engineering (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 4 h | 60 h |
| Pre/post processing | 15 | 6 h | 90 h |
| 150 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Exam Prepatation | 1 | 30 h | 30 h |
| 30 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
Integrated courses (lecture, exercise, seminar)
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Knowledge of the fundamentals of materials science or materials engineering are desired.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English, German |
| Duration/Extent | 90 |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter semester.
Maximum number of participants
The maximum capacity of participants is 50.
Registration procedures
Registration for the exam is carried out in accordance with the applicable version of the AllgStuPO.
Registration for the exam is done online via QISPOS.
Registration for the exam is done online via QISPOS.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
No recommended literature given
Assigned programs
This module is not used in any program.
Miscellaneous
Not specified