In times of rapid urbanisation and digital transformation, the use of geospatial data and artificial intelligence (AI) is crucial to tackle global challenges such as sustainable urban planning, climate adaptation and environmental monitoring. This course provides MSc and PhD students with practical insights into analysing geographic data, AI-powered methods and modern research data management.
The course covers analysing urban transformations through geospatial data sources such as volunteered geospatial information (VGI), social media geospatial information (SMGI) and earth observation (EO) data. Participants will learn how machine learning and deep learning methods can be applied to geographic issues. Practical examples include flood detection with Sentinel-1 data, analysing road networks with OSMnx and the use of neural networks for ship detection in radar images. Forecasting models for urban developments and environmental changes, such as water level forecasts and analyses of property markets, will also be presented.
The course uses interactive learning materials, including Python-based Jupyter notebooks and accompanying videos in MOOC format. This combination teaches theoretical principles and practical applications that are transferable to real-life research projects.
At the end of the course, participants will be able to process, analyse and visualise heterogeneous geodata, implement machine learning algorithms such as Random Forest or Support Vector Machines and build simple neural networks for geographic applications. This course prepares students for interdisciplinary research and promotes the responsible use of digital innovations in earth and environmental science.
- Kursleiter/in: Torben Dedring
- Kursleiter/in: Claudia Friederike Elisabeth Lindner
- Kursleiter/in: Andreas Rienow
- Kursleiter/in: Lars Tum