The autumn school provides an overview of state-of-the-art machine-learning techniques for geospatial and environmental analysis and modelling.

These methods promise to better account for nonlinearities, higher-order interactions, high dimensionality, and noisy data than ‘traditional’ statistical methods, offering improved predictive capabilities for decisio-making in environmental management for sustainability.

The course also introduces the programming language R with its geospatial capabilities and machine-learning extensions, and students will apply the acquired skills using real-world geospatial data sets and hands-on exercises.

Requirements

The event targets students of geographic information science, geography, earth and environmental sciences, engineering and related disciplines at the senior undergraduate level (last year of Bachelor), Master’s level, or Ph.D. level.
Staff are also welcome to apply.

Selection criteria:

• You need to be enrolled as student or PhD student, or be staff at an EC2U university in October 2023.
• Your Level of English needs to be at least B2.
  More information on the CEFR levels here: https://europa.eu/europass/system/files/2020-05/CEFR%20self-assessment%20grid%20EN.pdfExternal link
• You need to have prior knowledge of basic statistical methods (e.g., multiple linear regression), GIS or geospatial data, and (ideally) basic programming skills (e.g., R or Python).

The Autmn School is generously supported by grants from EC2U mobilities. For detailed information contact your EC2U coordination office at your university.