Climate AI Nordics

Climate AI Nordics

Nordic network for collaborations around tackling climate change using AI and machine learning.

PhD position: Determining the utility of newly available hyperspectral satellite data to better understand and quantify biochemical and biophysical properties of tundra vegetation negatively impacted by changing climatic conditions.

Tundra vegetation is being impacted by extreme climatic changes now influencing much of the Arctic. Increased temperatures, change in season length, and altered precipitation patterns affect plant health, biomass, and species composition. Satellite data are used to observe changes in tundra vegetation, and hyperspectral data have the potential to provide detailed insights into tundra vegetation’s biochemical and biophysical properties.

This PhD project aims to determine the utility of newly available hyperspectral satellite data to better understand and quantify biochemical and biophysical properties of tundra vegetation negatively impacted by changing climatic conditions. The study areas will be located in the Swedish tundra area. Research questions to be addressed are, for example, can biochemical and biophysical properties of tundra vegetation associated with a drier and warmer climate be detected using hyperspectral satellite data? Can hyperspectral satellite data be used to detect tundra plant diversity? Is there a benefit to synergistic use of data from hyperspectral and multispectral satellites?

The student will be placed at the Department of Earth Sciences. This PhD position is financed primarily by the Swedish National Space Agency. The PhD student’s specific research questions and approaches will be developed in collaboration with the supervisory team at the start of the PhD project.

Specific tools and techniques that may be included in the research project include:

  • Remote sensing data collection, processing, and analysis at multiple scales, including terrestrial, UAV, and satellite data, with emphasis on hyperspectral sensors
  • Lab-based chemical analysis of plant material
  • Field inventory of tundra vegetation
  • Geospatial data analysis including machine learning
  • Multivariate statistics
  • Writing scripts (e.g., using Python or R) for data processing and analysis

Deadline: January 19th, 2026

Apply here!

You May Also Enjoy

Reflections on the first EurIPS and a successful AICC workshop

Published:

Climate AI Nordics joined the inaugural EurIPS conference in Copenhagen last week, connecting with the community at our booth shared with the Nordic AI Partnership and Pioneer Centre for AI. On Saturday, we successfully hosted the full-day AICC workshop, featuring an inspiring lineup of speakers and over 30 posters bridging machine learning and climate science. While the research highlights covered diverse topics like weather forecasting, a significant portion of the program focused on analyzing forests as vital carbon sinks and biodiversity havens. We are grateful to our partners and all amazing researchers from around Europe and the rest of the world for supporting this memorable week of collaboration, glögg, and impactful science.

Reflections on the first EurIPS and a successful AICC workshop

Published:

Climate AI Nordics joined the inaugural EurIPS conference in Copenhagen last week, connecting with the community at our booth shared with the Nordic AI Partnership and Pioneer Centre for AI. On Saturday, we successfully hosted the full-day AICC workshop, featuring an inspiring lineup of speakers and over 30 posters bridging machine learning and climate science. While the research highlights covered diverse topics like weather forecasting, a significant portion of the program focused on analyzing forests as vital carbon sinks and biodiversity havens. We are grateful to our partners and all amazing researchers from around Europe and the rest of the world for supporting this memorable week of collaboration, glögg, and impactful science.

Featured member, December 2025: Laura Ruotsalainen

Published:

Laura Ruotsalainen is a Professor of Computer Science at the University of Helsinki and leads the Spatiotemporal Data Analysis research group. Her work focuses on developing machine learning methods for spatiotemporal data, particularly in reinforcement learning, representation learning, and uncertainty-aware models, motivated by challenges in climate, sustainability, and urban resilience. She also serves as Vice-Chair of the ELLIS Institute Finland and is a steering group member of the Finnish Center for Artificial Intelligence (FCAI)