Teaching
Our team contributes to teaching and curriculum development at Lund University within the areas of geospatial AI and data science. We offer guest lectures, workshops, and supervision as part of university education and outreach initiatives, and engage in educational collaboration with partner universities and research networks.
-
Machine Learning for Water Engineers
VVR080F, 7.5 credits
The aim of the course is to introduce machine learning algorithms for water applications. The course includes lectures as well as laboratory sessions on the Python programming language for students lacking sufficient programming skills.
View course detailsOfficial LTH doctoral course syllabus for VVR080F (fukurser.lth.se) (opens in a new tab)
Aim
The aim of the course is to introduce machine learning algorithms for water applications. The course includes lectures as well as laboratory sessions on the Python programming language for students lacking sufficient programming skills. The course is multidisciplinary involving guest lecturers from different departments, covering various applications of machine learning in solving water-related problems e.g., spatial and temporal modeling of water quality and quantity, as well as developing early-warning systems. The course also includes group projects where the students have the opportunity to work on real-world water-related issues and get hands-on experience.
Goals
Knowledge and Understanding
For a passing grade the doctoral student must
- Be able to widely describe the challenges and opportunities of the application of machine learning in the water context.
- Be able to comprehensively explain basic knowledge of machine learning e.g., supervised, and unsupervised learning, training classification, and regression algorithms.
- Be able to concretely describe the ideas behind the state-of-the-art machine learning algorithms.
- Be able to explain how machine learning-based frameworks can be developed for spatial and temporal modeling of water quantity, and quality, as well as early-warning systems.
Competences and Skills
For a passing grade the doctoral student must
- Be able to independently handle and analyse data using Python programming language.
- Be able to creatively and actively work as an individual and in a team to develop machine learning-based frameworks and apply them to solve water-related problems.
- Be able to scientifically evaluate and validate the performance of machine learning algorithms for water applications.
- Be able to scientifically and actively interpret and discuss the results from machine learning algorithms.
- Be able to write reports, and present the group project in a scientific, and technical manner.
Judgement and Approach
For a passing grade the doctoral student must
- Be able to evaluate and give constructive feedback to the developed machine learning-based frameworks by other groups in the class.
- Be able to show knowledge of the possibilities and limitations of machine learning for the water engineering context.
- Be able to actively relate the course content to their own Ph.D. project or a related topic.
Course Contents
Introduction and foundation of the state-of-the-art machine learning algorithms. Introduction to Python programming language. Computer laboratory sessions to help students get hands-on experience with Python programming language and the application of machine learning algorithms. Guest lectures on the application of machine learning for water-related issues based on the students thesis topics, and available guest lecturers. e.g., spatial and temporal modeling of water quality and quantity, as well as developing early-warning systems. Group projects on real-world water-related problems. Seminar session, and opposition.
Course Literature
Lindholm, A., Wahlström, N., Lindsten, F. & Schön, Thomas B.: Machine Learning, A First Course for Engineers and Scientists. Cambridge University Press, 2022.
The book "Machine Learning: A first course for engineers and scientists" is suitable for engineering students. The literature also includes three other books on machine learning and Python programming as well as scientific papers:
- Andreas Lindholm, Niklas Wahlström, Fredrik Lindsten and Thomas B. Schön: Machine Learning, A First Course for Engineers and Scientists. Available online at http://smlbook.org/ (opens in a new tab)
- Hastie, T., Tibshirani, R., Friedman, J.H. and Friedman, J.H., 2009. The elements of statistical learning: data mining, inference, and prediction (Vol. 2, pp. 1-758). New York: Springer.
- Géron, A., 2022. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media, Inc.
- Downey, A., Wentworth, P., Elkner, J. and Meyers, C., 2016. How to think like a computer scientist: learning with python 3. Available online at https://openbookproject.net/thinkcs/python/english3e/ (opens in a new tab)
- Scientific papers will also be used in the course based on the students' disciplines.
Instruction Details
Lectures, seminars, laboratory exercises, and project work. Assignments, exercises in laboratory sessions, group projects, and seminars.
Examination Details
Examination formats: written report, written assignments, and seminars given by participants. Grading scale: Failed, pass.
Admission Details
Admission requirements: the applicant must be a PhD student. Assumed prior knowledge: basic mathematics, including probability theory and statistics. Limited number of participants: maximum 20; the course can be canceled if there are fewer than 5 registered participants at the start of the course. In case of more applicants than the limit, students in Water Resources Engineering (TVRL) will be given priority.