Last modified: 05 Aug 2021 13:04
This module is designed to give students a range of skills associated with data-driven approaches and machine learning. Machine learning has revolutionised numerous scientific fields and it has begun to change the paradigm in geosciences by providing real-time solutions to non-trivial and computationally intense problems. Throughout the module the students will become familiar with the basic concepts and tools of machine learning. This will open up multiple career paths in geoscience and STEM in general.
| Study Type | Postgraduate | Level | 5 |
|---|---|---|---|
| Session | Second Sub Session | Credit Points | 15 credits (7.5 ECTS credits) |
| Campus | Aberdeen | Sustained Study | No |
| Co-ordinators |
|
||
The course will provide the students with the essential skills for conceptually understanding and implementing machine learning approaches to geophysical and geological problems.
In particular, the course will start from the very basic concepts such as machine learning for regression and classification using simple neural networks and support vector machines. Subsequently, the student will become familiar with unsupervised learning and how to apply it for reducing the dimensions of the data. More advanced topics will be discussed such as optimisation methods in machine learning and techniques to mitigate overfitting. Lastly, recent advancements in machine learning and how to apply them in geophysical problems will be discussed i.e deep learning, convolutional neural networks, recurrent neural networks, long short-term memory and generative adversarial networks.
The lectures will be combined with practical sessions where the students will learn how to use Python tools to design machine learning solutions from scratch. Various datasets from different geological/geophysical problems will be provided in order for the students to practice in a diverse set of problems and learn how to apply machine learning accordingly. Within that context, introductory sessions will be given on Python with emphasis on data analysis and machine learning.
Information on contact teaching time is available from the course guide.
| Assessment Type | Summative | Weighting | 50 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Feedback via MyAberdeen and email. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Assessment Type | Summative | Weighting | 25 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Feedback via MyAberdeen and email. |
Word Count | 3000 | |
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Assessment Type | Summative | Weighting | 25 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Feedback via MyAberdeen and email. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
There are no assessments for this course.
| Assessment Type | Summative | Weighting | 100 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback | ||||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Understand | Understand the methods and terminology related to Machine Learning and Deep Learning |
| Conceptual | Apply | Discover how Machine Learning is being applied to address geophysical problems |
| Procedural | Analyse | Gain more experience in coding |
| Procedural | Evaluate | Gain more experience in writing scientific literature reviews |
We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.
