- Resilience assessments
- Geodata analysis
- Machine learning
- Ecosystem assessments
- Remote sensing
- Big data
Nielja Knecht's research focuses on early detection of resilience loss in global ecosystems and identifying drivers using remote sensing data and machine learning
As part of her PhD, Nielja Knecht is developing methods to conduct high-resolution global assessments of resilience losses and impeding regime shifts in natural ecosystems. Using remote sensing data and machine learning approaches, she aims to improve the early detection and classification of these environmental changes and identify major climatic and anthropogenic drivers and thresholds for local and regional resilience losses.
Knecht holds a BSc and an MSc in Environmental Science from ETH Zurich, where she built a broad basis in sustainability sciences with a focus on biogeochemistry and data analysis. For her thesis project, she developed a machine learning model ensemble to assess the distribution of different groups of calcifying zooplankton and their contribution to the marine carbon export.
During her studies, Knecht spent one semester at the University of New South Wales in Sydney focusing on marine science and oceanography, and another one at the University of Gothenburg. In a number of internships ranging from community-based reforestation efforts in the Brazilian Amazon via sustainable infrastructure planning in the UK to assessments of urban biodiversity in Málaga, Knecht gained insights into a range of fields related to sustainable development.