| Unit name | Data-driven Physical Modelling |
|---|---|
| Unit code | SEMTM0007 |
| Credit points | 20 |
| Level of study | M/7 |
| Teaching block(s) |
Teaching Block 1 (weeks 1 - 12) |
| Unit director | Dr. Szalai |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
SEMT10002 Computer Programming and Algorithms (or equivalent) CADE10003 Engineering Science A (or equivalent) CADE10004 Engineering Science B (or equivalent) EMAT20200 Engineering Mathematics 2 |
| Units you must take alongside this one (co-requisite units) |
None |
| Units you may not take alongside this one |
None |
| School/department | School of Engineering Mathematics and Technology |
| Faculty | Faculty of Engineering |
The unit will provide a comprehensive introduction to the field of data-driven mathematical modelling. Students will learn how parsimonious and interpretable mathematical models can be extracted from data and how existing models can be parametrised using data.
Why is this unit important?
There are many phenomena that cannot be accurately described by bottom-up, first-principles based models, either because they are too complex to account for all details or because the parameters of the underlying models (for example, friction or magnetic hysteresis) are difficult to determine. In such scenarios mathematical models must be built and parametrised using available data. The mathematical models then can be used to guide further investigation, make design decisions or predict phenomena among other purposes.
How does this unit fit into your programme of study
The Engineering Mathematics programmes equip students to become mathematical modellers who are competent in solving real-world problems and truthfully interpreting data. This unit makes this process formal and equips students with the state-of-the art tools that make the mathematical modelling process rigorous. This unit will also have a broad engineering focus and an emphasis on practical methods; as a result, it will be suitable for students on other programmes with an interest in quantitative methods for modelling real systems.
An overview of content
The unit teaches a series of model identification, data assimilation and data-driven reduced order modelling techniques. The main objective is to be able to compare and contrast various methodologies and determine the approach that is fit for targeting a specific application.
This unit will start with an overview of the practical uses of mathematical models and standard techniques to obtain mathematical models. The techniques covered include topics such as principal component analysis, compressed sensing, neural ODEs, universal ODEs, autoencoders, dynamic mode decomposition and reservoir computing. The unit also discusses the functional representation of models and optimisation techniques suitable to determine model parameters.
Learning Outcomes
On successful completion of this unit, a student will be able to:
1. Choose an appropriate data-driven modelling framework that aligns with the problem specification and provides the required accuracy and/or interpretability of the model.
2. Demonstrate mastery of a data-driven modelling technique through the analysis of a synthetic or experimental data set
3. Use appropriate techniques to generate and prepare data for modelling purposes
4. Assess the quality of a mathematical model using metrics such as accuracy, repeatability, and generalisation
5. Demonstrate awareness and active consideration of ethical and responsible innovation principles with regards to data collection, use of data, and model construction
Teaching will be delivered through a combination of synchronous and asynchronous sessions, including video lectures, on-campus lecture/Q&A sessions, and formative self-directed exercises. The unit will be supported by weekly computer labs; these will provide student-centred on-campus learning through practical problem solving and, a supportive environment where students apply for themselves the theory and methods discussed in the unit. Students will be expected to actively participate in the lectures and labs, and engage with readings, self-directed exercises, and problem-solving activities.
How you will be assessed
The assessment consists of an individual coursework submission and an exam. The coursework covers learning outcomes 2,3 and 5; the exam assesses learning outcomes 1 and 4.
Tasks which help you learn and prepare you for summative tasks (formative):
To prepare for the exam, worksheets will be provided about the theoretical part of the material on a regular basis. The contents of the lectures and computer labs will also provide direction on how to demonstrate the learning outcomes in the coursework assessment.
Tasks which count towards your unit mark
When assessment does not go to plan
Re-assessment takes the same form as the original summative assessment.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. SEMTM0007).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The assessment methods listed in this unit specification are designed to enable students to demonstrate the named learning outcomes (LOs). Where a disability prevents a student from undertaking a specific method of assessment, schools will make reasonable adjustments to support a student to demonstrate the LO by an alternative method or with additional resources.
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
