Project summary

Early detection of abiotic/biotic vegetation stress/damage is a challenging topic, especially in context of such topical stressors as climate warming, drought, bark beetle infestation etc. The availability of high-resolution (aerial, UAV) hyperspectral and thermal data and the flexibility of these remote sensing technologies (especially possibility of high temporal resolution) has increased the chance of remote sensing to provide reliable early warning indicators of vegetation stress (health status). Physiological indicators such as photosynthetic pigments, water content or vegetation temperature can provide valuable information, especially in conjunction with radiative transfer modelling techniques. However, there are still significant challenges for remote sensing community such as upscaling from leaf to canopy level, applying these methods for heterogeneous habitats, empirical validation of radiation–vegetation interactions or high computational demand in case of extensive areas assessment.

The Research Team of Image and Laboratory Spectroscopy is currently working on several projects dealing with vegetation health assessment. Very high resolution multitemporal UAV and aerial data for homogeneous and heterogeneous habitats will be acquired within these projects. Laboratory spectral measurements and laboratory biochemical data will also be collected. The goal of the PhD project will be to assess vegetation health status using radiative transfer modelling (based on high-resolution hyperspectral and thermal data), to test various models and also combine RTM with machine learning approaches focusing not only on homogeneous but also on heterogeneous ecosystems.

The applicant should have advanced knowledge in the field of remote sensing (the relevant PhD study program is “Applied geoinformatics, Cartography and Remote Sensing “) and should be strongly motivated to contribute for the team work on the described topic. Experience with some RTM models for vegetation health assessment and with deep learning approach/es and also programming skills in R or Python are an advantage. The tasks of the PhD student will be:

  • Participation in the fieldwork and spectroscopic laboratory measurements
  • Data pre-processing and analysis of vegetation health using RTM modelling on the leaf, canopy and habitat levels in combination with deep learning focusing on some of above-mentioned current challenges of radiative transfer modelling
  • Data interpretation and participation in the preparation of publications (at least 4 articles should be published within 4-years duration of the PhD studies in collaboration with other team members)

A scholarship for the PhD student will be 1000 EUR/month and special bonus will be paid after the publication of each article. The student can apply for special university project to increase the scholarship and get support for publication activities, data acquisition, travel expenses and internationalization (participations on conferences, foreign stays etc.)

Deadline is closed

Don’t hesitate, submit an application now!

Choose your specialization