Title: Inferring Standing Deadwood from Satellites

Research Area: Remote Sensing in Geo- and Ecosystem Research, Earth and Environmental Sciences

Forests are suffering and we observe tree die-off in a variety of regions in the world. Understanding the diverse causes of tree mortality requires exact information about which trees are dying and where. In parallel, satellites have become an invaluable to tool to measure the world’s ecosystems. The PhD project aims to leverage satellite data to improve our understanding on tree mortality.

Aims

The project “Inferring Standing Deadwood from Satellites” aims to develop a general model to quantify and locate standing deadwood in a variety of tree ecosystems using multi-spectral satellite data.

Problem

Satellite data presents multiple challenges such as coarse spatial and temporal resolution depending while tree mortality often happens on a much finer scale.

Technology

• Deep Learning, Transformers
• Hyperspectral imagery

Team

Lead

• Clemens Mosig

Team Members

• Miguel Mahecha
• Teja Kattenborn