Climate AI Nordics

Climate AI Nordics

Nordic network for collaborations around tackling climate change using AI and machine learning. NGO registered in Sweden.

Recap of the AICC-2 workshop at ECCV 2026 in Malmö


The 2nd Workshop on AI for Climate an Conservation (AICC-2), organized by Climate AI Nordics, took place on Sept 9th at ECCV 2026 in Malmö (Sweden), bringing together a packed room of researchers and practitioners working at the intersection of AI, climate, and conservation.

During this full-day event, the attendants got to listen to a great lineup of keynotes, where Devis Tuia, Nora Gourmelon, Bruno Sanchez-Andrade Nuño, Abdulhakim M. Abdi provided insightful and engaging presentations and discussions on topics such as video-based biodiversity monitoring (Devis), computer vision for monitoring the changing Arctic (Nora), geoAI-vs-just-AI (Bruno), and what is really needed for AI to deliver for nature conservation (Abdulhakim). These topics were further expanded on in an engaging panel discussion. The day also included a diverse set of oral & poster presentations.

On the evening after AICC-2, Climate AI Nordics also organized a vibrant AI for planetary health social at Cantin in Malmö. This was done in collaboration with Asterisk Labs, as well as the CV for marine vision and CV4Ecology communities (cudos to the people behind the organization: Mikolaj Czerkawski, Aleksis Pirinen, Rupa Kurinchi-Vendhan, Malte Pedersen, Jacqueline Campbell, Olof Mogren, Ankit Kariryaa, Nico Lang)! It was really great to see so many people working on these topics get together!

Published:

Categories:

You May Also Enjoy

Save the date: The 3rd Nordic Workshop on AI for Climate

Published:

Climate AI Nordics is happy to announce that our annual **_Nordic Workshop on AI for Climate_** returns again for a third time in 2027, this time in Oslo! Mark **April 22nd 2027** in your calendars, and stay tuned for more info to come!

Machine perception for scientific measurement from satellite imagery

Event date:

Webinar with Rangel Daroya, University of Massachusetts Amherst. In many scientific domains, the goal is not simply to classify an image or produce a visually plausible segmentation, but to estimate quantities that scientists and decision-makers can use: river width, water extent, sediment concentration, habitat change, or other physical variables. These tasks require models that are robust to distribution shift, efficient under limited supervision, and reliable enough to support downstream measurement. In this talk, I will discuss machine learning and computer vision methods for this setting, with a focus on geospatial imagery and hydrology. Scientific domains such as remote sensing expose several fundamental limitations of current vision systems. Models must operate across sensors, geographic regions, seasons, and acquisition conditions, often with limited labeled data and multispectral inputs that differ from standard natural image benchmarks. They must also detect small or thin structures, handle temporal variation, and avoid errors that may appear minor under conventional vision metrics but lead to substantial errors in scientific measurements. I will discuss three aspects that try to solve these problems: learning transferable representations that can adapt across tasks and datasets, developing data-efficient perception methods for multispectral and geospatial imagery, and translating model predictions into reliable physical measurements. I will highlight work on task transfer, satellite representation learning, river segmentation, and downstream estimation of river width and other hydrological variables. More broadly, this work aims to develop robust, transferable, and data-efficient machine perception systems that can turn large-scale satellite and scientific imagery into reliable measurements of the physical world.

Aurora: A foundation model of the Earth system

Event date:

Webinar with Ana Lucic, University of Amsterdam. Reliable forecasting of the Earth system is essential for mitigating natural disasters and supporting human progress. Traditional numerical models, although powerful, are extremely computationally expensive1. Recent advances in artificial intelligence (AI) have shown promise in improving both predictive performance and efficiency, yet their potential remains underexplored in many Earth system domains. Here we introduce Aurora, a large-scale foundation model trained on more than one million hours of diverse geophysical data. Aurora outperforms operational forecasts in predicting air quality, ocean waves, tropical cyclone tracks and high-resolution weather, all at orders of magnitude lower computational cost. With the ability to be fine-tuned for diverse applications at modest expense, Aurora represents a notable step towards democratizing accurate and efficient Earth system predictions. These results highlight the transformative potential of AI in environmental forecasting and pave the way for broader accessibility to high-quality climate and weather information. Link to paper: https://www.nature.com/articles/s41586-025-09005-y

Towards verified tree-level CO2 and H2O physiology, resolved at 30-min resolution

Event date:

Webinar with Jaime Caballer Revenga, University of Copenhagen. This project addresses one major challenge in climate science: accurately quantifying how forests remove carbon dioxide (CO₂) from the atmosphere. Forests currently account for nearly one-third of the global land carbon sink, but their capacity to absorb CO₂ is increasingly threatened by climate change(s), land-use change(s), and environmental disturbance(s). At the same time, afforestation, reforestation, and carbon offset initiatives are expanding rapidly, despite persistent concerns about the reliability and transparency of the methods used to estimate carbon sequestration. The INFOSCO project (Integrating Forest Structure and Carbon Observatories) proposes a new approach by shifting the focus from forest-scale carbon assessments to continuous physiological estimates at the level of individual trees. By combining ecosystem CO₂ flux observations, laser-based measurements of forest structure, and theory of plant physiological processes, it aims to estimate the contribution of each tree to overall forest carbon uptake. This will provide a more detailed and biologically grounded understanding of carbon sequestration while remaining consistent with established micrometeorological measurements and theory. Methodologically, the research integrates data and concepts from ecosystem ecology, laser proximal sensing, plant physiology, and statistical modelling into a unified framework. The core modelling strategy uses a Bayesian hierarchical structure to quantify uncertainties at multiple levels. By means of Dirichlet regression the method ensures that tree-level estimates are consistent with ecosystem-scale micrometeorological observations. Beyond improving carbon accounting, the project aims to bridge between detailed field-based ecological measurements and AI models scalable to biogeographic applications. By linking high-resolution observations of individual trees with ecosystem-atmosphere fluxes, it seeks to advance both our understanding of forest physiology and the development of more robust tools for monitoring and verifying nature-based climate solutions.