Module manager: Chetan Deva
Email: c.r.deva@leeds.ac.uk
Taught: Semester 2 (Jan to Jun) View Timetable
Year running 2025/26
The equivalent of A level maths and a good grounding in basic Python (equivalent to that achieved in SOEE5710, SOEE2810, SOEE2931).
This module is not approved as an Elective
Advances in machine learning in combination with a vast increase in remotely sensed observations of the earth system and geophysical data volumes are changing the way research is done. For example, data-driven weather forecasting models now rival state-of-the-art dynamical systems, achieving comparable accuracy at a fraction of the computational cost. Researchers of the future need to be able to understand the fundamentals of machine learning algorithms and be able to apply them in the context of geoscientific challenges. This course equips master’s students with foundational knowledge of statistics and practical machine learning skills, preparing them for their Master’s projects and future careers in both industry and academia.
On completion of this course, students will have gained a strong foundation in thinking through problems statistically. They will develop an understanding of the core statistical and machine learning methods employed in environmental, climate and geo- science and gain hands on experience of using these techniques on real world data. By the end of the course, they will have practical experience of developing end-to-end machine learning pipelines in Python and be ready to use the skills they have developed in both research and industry.
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:
SSLO1: Explain fundamental concepts in statistics and machine learning.
SSLO2: Apply a range of statistical methods including machine learning algorithms to environmental, climate and geoscience data.
SSLO3: Design machine learning pipelines in Python in the context of environmental, climate and geoscientific problems.
SSLO4: Evaluate, critically, the use of machine learning methods to relevant prediction problems.
Skills Learning Outcomes
On successful completion of the module students will have demonstrated the following skills learning outcomes:
SKLO1: Intermediate Python programming proficiency (Information Technology, Digital skills).
SKLO2: Using online resources to build upon the core proficiencies mastered in lectures and computer practicals (Active Learning, Working and academic skills).
SKLO3: Critical engagement with the literature (Referencing, Academic skills).
SKLO4: Hypothesis testing (Problem Solving, Work ready skills).
SKLO5: The ability to evaluate the performance of data-driven models (Critical Thinking, Work ready, Sustainability and Academic skills).
SKLO6: Coding reliable end to end Machine Learning pipelines (Information Technology, Work ready skills).
SKLO7: Time management, planning and organisation (Work ready and Academic skills)
Details of the syllabus will be provided on the Minerva organisation (or equivalent) for the module
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Lecture | 6 | 1 | 6 |
| Practical | 17 | 2 | 34 |
| Independent online learning hours | 45 | ||
| Private study hours | 65 | ||
| Total Contact hours | 40 | ||
| Total hours (100hr per 10 credits) | 150 | ||
Worksheets are completed weekly in either the lectures or seminars. The majority of worksheets will be Python notebooks, completed in the weekly computer practicals. Staff and demonstrators will be present to discuss students’ coding, help with the tasks and provide feedback on their solutions. This weekly formative feedback will help with performance in the assessed coursework.
| Assessment type | Notes | % of formal assessment |
|---|---|---|
| Coursework | Coursework | 60 |
| Coursework | Coursework | 40 |
| Total percentage (Assessment Coursework) | 100 | |
Normally resits will be assessed by the same methodology as the first attempt, unless otherwise stated
The reading list is available from the Library website
Last updated: 29/04/2025
Errors, omissions, failed links etc should be notified to the Catalogue Team