2024/25 Taught Postgraduate Module Catalogue

GEOG5304M Machine Learning for Environmental Data

15 creditsClass Size: 50

Module manager: Dr Arjan Gosal
Email: a.gosal@leeds.ac.uk

Taught: Semester 2 (Jan to Jun) View Timetable

Year running 2024/25

This module is not approved as an Elective

Module summary

This module offers the opportunity to explore machine learning, deep learning, and AI applications in environmental data analysis. Students will gain foundational knowledge in these areas and engage in critical discussions about issues such as data misrepresentation and experimental design flaws in data science. Emphasis is placed on the context-specific application of these technologies to large-scale environmental problems, fostering a comprehensive understanding of both technical and ethical dimensions of machine learning.

Objectives

This module aims to enable students to:

1. Critically assess and select appropriate machine learning methodologies for environmental data analysis.
2. Gain proficiency in various advanced machine learning techniques, with a focus on ethical considerations, result interpretation, and transparent communication.
3. Transcend technical learning by encouraging students to reflect on the broader implications and responsibilities associated with data analysis and insight generation.

Learning outcomes
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:

1. Critically evaluate various machine learning techniques, focusing on their applicability and limitations in environmental data analysis.
2. Apply a range of machine learning, deep learning, and AI techniques to real-world environmental datasets.
3. Distinguish between robust and misrepresentative outcomes in machine learning-based environmental studies.
4. Effectively communicate the process and results of machine learning analyses, limitations and potential impacts on environmental decision making.


Skills Learning Outcomes

On successful completion of the module students will have demonstrated the following skills learning outcomes:

1.Technical skills, i.e. demonstrating a critical understanding and application of advanced machine learning techniques.
2. Work ready skills, i.e. collaborative skills through group projects, preparing for team-oriented professional environments.
3. Sustainability skills, i.e. critical evaluation and analysis of findings from machine learning driven data analysis to make informed recommendations for societally relevant issues, e.g. those related to the SDGs.

Syllabus

Details of the syllabus will be provided on the Minerva organisation (or equivalent) for the module.

Teaching methods

Delivery type	Number	Length hours	Student hours
Lectures	8	1.00	10.00
seminars	3	1.50	4.50
Practicals	5	2.00	10.00
Private study hours			125.50
Total Contact hours			24.50
Total hours (100hr per 10 credits)			150.00

Opportunities for Formative Feedback

Formative feedback will be available to students in the practical computer labs, where staff and demonstrators will be present. In addition, common issues encountered and how to overcome them communicated to students post session via Minerva. The seminars are purely designed to allow critical discussion around key topics, and formative feedback will be given in terms of both content, but also how to critically evaluate.

Methods of assessment

Coursework

Assessment type	Notes	% of formal assessment
Assignment	Coursework	50.00
Assignment	Semi-guided report	50.00
Total percentage (Assessment Coursework)		100.00

Normally resits will be assessed by the same methodology as the first attempt, unless otherwise stated

Reading list

The reading list is available from the Library website

Last updated: 29/04/2024 16:14:37

Disclaimer

Browse Other Catalogues

• Undergraduate module catalogue
• Taught Postgraduate module catalogue
• Undergraduate programme catalogue
• Taught Postgraduate programme catalogue

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD