Module GEOG42130: Environmental Data Science

Department: Geography

GEOG42130: Environmental Data Science

Prerequisites

• None

Corequisites

• None

Excluded Combination of Modules

• None

Aims

• Equip students with the advanced data science skills necessary to analyse numerical and spatial environmental data (e.g. GIS, programming, modelling, statistical analysis).
• Familiarise students with a range of open source environmental data, and their applications.
• Enable students to identify the most suitable datasets and undertake the most appropriate form of analysis for a particular application/research question.

Content

• Recent advances in data acquisition and processing mean that we have transitioned from a data-poor to a data-rich view of environmental processes. This module aims to equip students with the skills needed to undertake insightful, efficient and reproducible analysis of these data enabling them to quantitatively explore real-world environmental challenges. These advanced data analysis skills could include statistical analysis, GIS, programming, modelling, and machine learning. Intensive introductions to skills will be provided at key points during the module. The module will include: applied examples that draw upon datasets that allow advanced insight to a range of environmental processes; analysis of datasets that are relevant for various Sustainable Development Goals and a range of environmental hazards; experience in using a range of online data sources at both local and global scales.
• Indicative content:
• Programming (data analysis)
• GIS scripting in Python
• Data visualisation
• Machine learning and deep learning
• Exploring open-source data sets that could include Google Earth Engine, ESA, NASA

Learning Outcomes

• The uses of different types of data and data analysis and how to select between them.
• How to assess the quality, uncertainty and appropriateness of different datasets.
• The availability, relative merits, and potential applications of various open-source environmental data.

• Analysing numerical and spatial data using skills including statistical analysis, coding and GIS.
• Identifying, evaluating and analysing open-source environmental data.
• Ability to identify and undertake the most appropriate form of analysis.

• Critical thinking and problem solving
• Written and other communication
• Advanced quantitative data analysis

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Lectures will introduce students to specific techniques, their relation to different kinds of data, and provide context for the accompanying computer lab session.
• Weekly computer lab sessions will focus on specific techniques, giving students hands on experience of the analysis of various kinds of data.
• Assessment will be via in class General Tests with a mix of question types focusing on identifying appropriate types of analysis, analysing data, including assessing its quality and uncertainty, and undertaking data analysis.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

There will be a formative short answer test in week 4 of the module. Feedback will be provided on the test, including a set of solutions and with generic information on each question. Feedback will also be provided during the computer lab sessions.

■ Students who do not attend monitored activities shown under Teaching Methods and Learning Hours, or who fail to complete the summative or formative assessment(s) specified above, may be subject to the Academic Progress procedures defined in the University's General Regulation V, and may be required to leave the University.