MSc Data Science (Earth and Environmental Analytics)

Year of entry: 2024

Course unit details:
Earth and Environmental Data Science

Course unit fact file
Unit code EART60702
Credit rating 15
Unit level FHEQ level 7 – master's degree or fourth year of an integrated master's degree
Teaching period(s) Semester 2
Available as a free choice unit? No


In this hands-on course unit, students will develop their skills in understanding the concepts behind Earth and Environmental Data Science, with a focus on using Python programming to analyze and visualize environmental data. Students will learn data curation skills and explore topics such as air quality and climate change. Throughout the course, students will work with Python programming concepts and packages including xarray, scikit-learn, and PyTorch. Students will also have the opportunity to learn about computer clusters and high-performance computing using university resources Three projects are designed to help students improve their programming skills and gain a deeper understanding of Earth and Environmental Science concepts, with group work highly encouraged. Students are expected to manage the use of GitHub for conducting these projects and collaborating with their peers on GitHub. A scientific literature presentation is designed to help students comprehend cutting-edge data science applications in Earth and Environmental Sciences.


By the end of the course, students will have the knowledge and tools necessary to solve realistic problems in Earth and Environmental Sciences using data-driven approaches.


Provide an understanding of important aspects of Earth and Environmental Data Science which are often overlooked in typical Data Science or Earth and Environmental Sciences courses. This unit provides a firm foundation and hands-on experience in data curation, data analytics, data visualization, and computing for Earth and Environmental applications.

Learning outcomes

  On the successful completion of the course, students will be able to: Developed Assessed
ILO 1 Describe data curation, data analytics, data visualization, and computing methods and tools using industry standards in coding and curation practices.    
ILO 2 evelop the skills to find and manage Earth and Environmental data (e.g., weather and climate data) from a range of sources and process data to explore and answer questions related to environment, weather and climate.    
ILO 3 Develop an awareness of open science and open source communities and how to contribute to them by creating fully transparent and reproducible open-source data science projects.    
ILO 4 Perform exploratory data analysis and use visualization to enhance interpretation of data, including maps and interactive visualizations.    
Construct complete, well-structured programs in Python and practice reproducible research.



Week 1: 
- Introduction to Earth and Environmental Data Science
- Introduction to JupyterLab and Git Fundamenental
- Review of Python: NumPy, Pandas, and Basic Operation of Environmental Datasets

Week 2:
- Data Analytics I: Dataframe Computation, Time and Date Functionality (e.g. NumPy and Pandas)
- High level multidimensional gridded data using Xarray

Week 3:
- Data Analytics II: Review of Statistics
- Data Visualization: Principle and Tools (e.g. Matplotlib, Seaborn)

Week 4:
- Reproducible Research (e.g. Binder, Markdown)
- Project 1 (data visualization + data analytics) Presentation

Week 5:
- Introduction to Unix
- Managing Python Environments
- Git Advanced

Week 6:
- Online Repository of Earth and Environmental Science Data
- Remote Sensing Data: Google Earth Engine and geemap
- Climate Data: Climate Change Service

Week 7:
- Supervised Learning and Automated Machine Learning
- Unsupervised Learning
- Applications of Machine Learning in Earth and Environmental Sciences

Week 8:
- Organization and Packaging of Python Projects
- Advanced Data Visualization (e.g. Cartopy)

Week 9: 
- Project 2 (reproducible research) Presentation

Week 10:
- A Taste of Deep Learning

Week 11:
- High-Performance Computing and Dask for Parallel Computing
- Scientific Literature Presentation (Machine Learning for Earth and Environmental Science session I)

Week 12:
- Summary
- Scientific Literature Presentation (Machine Learning for Earth and Environmental Science session II)

Teaching and learning methods

Other Scheduled teaching and learning activities:

  • Revision workshops/surgeries
  • Online discussions/tutorials
  • Meetings with Academic Advisers
  • Field trips

Assessment methods

Method Weight
Other 35%
Report 30%
Project output (not diss/n) 35%

Feedback methods

Assessment task Length How and when feedback is provided Weighting within unit (if relevant)

Data Science Projects and Presentations 

Data Science Projects and Presentations 
•    Project 1 (week 4) 
•    Project 2  (Week 9) 
•    Literature Review (Weeks 11,12) 

Project 1 and 2 
Submit code, Group presentation (10 minutes) 
Individual reflective write up (Max 500 words) 
Literature review
Individual presentation (10 minutes) 
Feedback from the instructor and peers (each group) Project 1 35% 
Project 2 35% 
Literature Review 30% 


Recommended reading


  • Python for Probability, Statistics, and Machine Learning (3rd Edition):


Teaching staff

Staff member Role
Zhonghua Zheng Unit coordinator

Return to course details