Machine learning for spatial data

You are here

PERC met WIMEK nieuw logo.png

Machine learning for spatial data

To be announced


sem.jpgIn this course, participants will learn how to model patterns and structures contained in data. The course will be focused on statistical and machine learning approaches, where the relationships between the observed data and the phenomenon under study are learned directly from observations.

The course will focus on aspects of:

  • data representations
  • feature extraction / reduction
  • clustering
  • semantic classification

Through a series of lectures and practical exercises (in Matlab), the participants will learn about different strategies and their pertinence for specific problems in environmental sciences. Most applications considered in the course will be remote sensing-based, but the course will remain general for a broader audience.

Tentative Programme
  • Day 1 - morning: Introduction to machine learning, best practices
  • Day 1 - afternoon: Introduction to Matlab scripting
  • Day 2 - morning: lectures on clustering
  • Day 2 - afternoon: practical on clustering
  • Day 3 - morning: lectures on feature extraction and spatial context
  • Day 3 - afternoon: practical on feature extraction and spatial context
  • Day 4 - morning: lectures on supervised classification
  • Day 4 - afternoon: practical on supervised classification
  • Day 5 - morning: lectures on exciting new research topics (structured prediction / deep learning)
  • Day 5 - afternoon: DIY session - come and discuss your data mining problem and design a relevant pipeline
General information
Target Group The course is aimed at PhD candidates, postdocs, and other academics that are interested in machine learning applied to spatial data
Group Size Min. 15 / Max. 25 participants
Course duration 5 days
Language of instruction English
Frequency of recurrence To be determined
Number of credits 1.5 ECTS
Lecturers Dr Devis Tuia (Laboratory of Geo-Information Science and Remote Sensing, Wageningen University & Research)
Prior knowledge Basic skills in statistics are a plus. The practicals will be in Matlab. A short introduction will be provided on the first day, but previous experience in Matlab or R or Python is required.
Location Wageningen University Campus
Options for accommodation Accommodation is not included in the fee of the course, but there are several possibilities in Wageningen. For information on B&B's and hotels in Wageningen please visit Another option is Short Stay Wageningen. Furthermore Airbnb offers several rooms in the area. Finally, there is also a very active public Facebook group called “Wageningen Student Plaza”, where rooms are often offered for short-term sublets, but where one could also easily post a request for renting a room for a week in Wageningen. Finally, note that besides the restaurants in Wageningen, there are also options to have dinner at Wageningen Campus.
More information

Dr. Lennart Suselbeek (PE&RC)
Phone: +31 (0) 317 485426

Registration of interest

At this moment, this course is not scheduled yet. However, if you register your interest in this activity below, we will inform you as soon as the course is scheduled and registration of participation is opened.