ENLIGHT joint courses

Deep Learning in Forestry 2025

Forests are an important part of our ecosystems and produce a large part of the air we breathe. It is important to monitor and survey forests and trees. Using Artificial Intelligence for monitoring and surveying of forests is one way to reduce costs and interpret different kinds of data (color and hyperspectral images). Recent progress in Artificial Intelligence through Neural Networks and Deep Learning means more widespread applications are now at hand and the exploitation of large amounts of data.

About the course

Content

Satellite Earth observation has become a key technology in forest monitoring. With the European earth observation program Copernicus, a program exists that provides access to temporally high-resolution and freely available satellite images, and this worldwide. New analysis methods are needed to deal with the huge amounts of data; machine learning offers excellent opportunities here. Even with UAVs, huge amounts of data are often generated when, for example, ground resolutions of 2 cm are used. Concrete evaluation topics are e.g. the detection of game damage or the differentiation of tree species.

Topics which will be addressed:

  • Introduction to Python and Tensorflow Keras
  • Introduction to classical machine learning and deep Learning
  • Deep Learning architectures and their application fields
  • Exemplary forestry applications 
  • Deep Learning with Python and Keras

The skills learned in this course also transfer to many other application fields that use image or video data.

Learning outcomes

In this module, students acquire key qualifications for the use of Deep Learning algorithms for forestry applications, which is also transferable to other applications in other disciplines. They learn the principles of Deep learning as well as neural networks and their optimisation. You will develop an understanding of which problems can be solved with the methods of Deep Learning and which methods should be selected. After completing the module, the students are able to freely program Deep Learning applications in Python. They can independently implement existing neural networks and handle implement existing neural networks and deal with large amounts of data.

Programme

To be announced after registration. Tentative program includes lectures on AI and Deep Learning, Data Science and Image Processing with Python, Forestry, and sessions on Intercultural Competence.

Assessment

Assessment will be through a project to be developed during the on-site period and afterwards. There will be a presentation on the last on-site day, and a final report that will be graded and completes the course.

Transcript of Records will be provided a month after the course ends.

Lecturers

  • Dr. Nils Nölke / Dr. Lutz Fehrmann (University of Göttingen)
  • Prof. Dr. Jean-Christophe Taveau (University of Bordeaux)
  • Prof. Dr. Matias Valdenegro Toro (University of Groningen)

Plus lecturers from University of Groningen and University of Bordeaux.

Course dates

On-site period: March 17 - March 21 in Bordeaux.

Online period: January 13 -  February 23. Details to be announced.

Please note that the application deadline mentioned below can be different in your home institution.

  • Courses – Focus area: Digitalisation
  • Study Field: Science and Technology
  • Type: blended intensive programme (Erasmus+ funding)
  • Host: University of Bordeaux
  • Course dates: 13 January - 21 March 2025
  • Apply by: 15 November 2024
  • ECTS: 6
  • Number of places available: For University of Göttingen, Groningen & Bordeaux: 10 per partner. Other universities: can place students on the waiting list.
  • Level: Bachelor 3, Master 1, Master 2