This seminar is a collaboration between RISE and Climate AI Nordics – climateainordics.com.

Title: EarthShift: A benchmark for real-world ditribution shifts in Earth observation

Speaker: Kelsey Doerksen, University of Cape Town and Arizona State University

Abstract: Geospatial Foundation Models claim to offer powerful solutions to simplify and accelerate real-world problems, enabling the capabilities to monitor, analyze, and predict changes on our planet. Current Earth Observation benchmarks to quantify the performance of these models focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. However, when models are deployed, they must generalize to many out-of-distribution scenarios, such as new time periods, geographies, and sensors; and in many contexts, these models are brittle. We introduce EarthShift: the first public testbed for benchmarking robustness across multiple realistic distribution shifts encountered in remote sensing. EarthShift enables users to measure distributional robustness by comparing performance in- and out-of-distribution using datasets from paired data sources, temporal windows, geographic locations, and sensors. EarthShift provides a testbed to guide future work to create foundation models that are robust and reliable in real-world applications.

About the speaker: Kelsey Doerksen is a joint postdoctoral fellow at the University of Cape Town's Climate Risk Lab and Arizona State University in the School of Augmented Intelligence and Computing and research affiliate at the NASA Jet Propulsion Laboratory. Her research focuses on combining her expertise in AI, Earth Observation, and Foundation Models to applied problems in the climate, food security, and biodiversity domains. She is a recent graduate from the Autonomous Intelligent Machines where she completed her thesis in the Oxford Applied and Theoretical Machine Learning Group on "Applied Machine Learning for Earth Systems Science", collaborating with the United Nations, European Space Agency and NASA during her PhD.

Location: This is an online seminar. Connect using Zoom.

Date: 2026-05-28 15:00

Upcoming seminars:

• 2026-06-11: More is different: emergent social conventions and tipping points in AI populations, Gustau Camps-Valls, University of Valencia
• 2026-06-25: More is different: emergent social conventions and tipping points in AI populations, Markus Reichstein, Max-Planck-Institute for Biogeochemistry and ELLIS Unit Jena
• 2026-08-27: More is different: emergent social conventions and tipping points in AI populations, Ariel Flint Ashery, City St George’s, University of London
• All seminars are 15:00 CET.

More information and coming seminars: https://ri.se/lm-sem

– The Learning Machines Team

This seminar is a collaboration between RISE and Climate AI Nordics – climateainordics.com.

Title: Understanding the complex Earth system with Machine Learning and Hybrid Modelling

Speaker: Markus Reichstein, Max-Planck-Institute for Biogeochemistry and ELLIS Unit Jena

Abstract: The Earth system is a complex, dynamic and strongly interconnected system, shaped by interactions between climate, ecosystems, biogeochemical cycles and human activities. Rapidly growing streams of satellite, in-situ and experimental observations, together with advances in machine learning, offer new opportunities to detect patterns, infer processes and improve prediction across scales. Yet purely data-driven approaches often lack physical consistency and interpretability, while classical process-based models remain limited by uncertain parameterizations and incomplete representations of complex feedbacks.

In this talk I will discuss how machine learning and hybrid modelling can help bridge this gap. By combining the versatility of data-driven methods with the constraints and explanatory power of mechanistic understanding, hybrid approaches can support more robust, interpretable and physically consistent models of the Earth system. Examples from the terrestrial biosphere, land-atmosphere exchange, carbon and water cycles, and climate extremes will illustrate how such approaches can contribute not only to improved prediction, but also to deeper scientific understanding of Earth system dynamics.

About the speaker: Markus Reichstein is Director of the Biogeochemical Integration Department at the Max Planck Institute for Biogeochemistry and Professor for Global Geoecology at FSU Jena. His primary research interests center on how ecosystems respond and feedback to climatic variability, with a particular focus on the interplay between climate extremes and ecosystem resilience. To address these complex challenges, he combines artificial intelligence and system modeling approaches to exploit extensive ground- and satellite-based Earth observations. He is Program Director of the ELLIS Machine Learning for Earth and Climate Sciences program and founding Director of the ELLIS Unit Jena. Notably, he has served as a lead author for the IPCC Special Report on Climate Extremes (SREX) and was awarded the prestigious Gottfried Wilhelm Leibniz Prize in 2020. His groundbreaking collaborative research has also been supported by a major European Research Council (ERC) Synergy Grant.

Location: This is an online seminar. Connect using Zoom.

Date: 2026-06-25 15:00

Upcoming seminars:

• 2026-08-27: More is different: emergent social conventions and tipping points in AI populations, Ariel Flint Ashery, City St George’s, University of London
• All seminars are 15:00 CET.

More information and coming seminars: https://ri.se/lm-sem

– The Learning Machines Team

This seminar is a collaboration between RISE and Climate AI Nordics – climateainordics.com.

Title: A Critical Look at Explainable AI

Speaker: Gustau Camps-Valls, University of Valencia

Abstract: I will give a sarcastic and quite op-ed tour trying to explain why XAI is misleading us. Everything from SHAP plots to counterfactuals may look trustworthy, but underneath, they're often driven by correlations, not causation. In fields like climate, neuroscience and social sciences, that's a serious risk. Inspired by philosophy of science, I argue that explanations must go beyond surface patterns. Fortunately, the frontier is moving fast: causal‐informed SHAP, meaningful counterfactuals (you can't go younger), causal certification in explanations, and structural causal modeling are all promising. Yet, it's time we treat XAI not just as a cosmetic fix, but as a tool grounded in truth: seamful, thought-provoking, and scientifically defensible. And if time allows I'd like to say a few words about why AI needs a new philosophy of science.

About the speaker: Gustau Camps-Valls is a Full Professor of Electrical Engineering at the Universitat de València, where he leads the Image and Signal Processing (ISP) group. His research lives at the intersection of machine learning and Earth system science, focusing on combining deep learning with physical laws to better model and understand climate change. A widely recognized global leader in his field, he is Program Director of the ELLIS Machine Learning for Earth and Climate Sciences program. He is a Fellow of the IEEE, ACM, AGU, and Academia Europaea, and a highly cited researcher. His work has been supported by prestigious European Research Council (ERC) Consolidator and Synergy grants, and he was recently awarded the 2025 Blaise Pascal Medal. Beyond his research, he serves as a convener for the United Nations’ ITU AI for Good seminar series and holds visiting positions at the Institut Polytechnique de Paris and the Max Planck Institute. https://isp.uv.es

Location: This is an online seminar. Connect using Zoom.

Date: 2026-06-11 15:00

Upcoming seminars:

• 2026-06-25: More is different: emergent social conventions and tipping points in AI populations, Markus Reichstein, Max-Planck-Institute for Biogeochemistry and ELLIS Unit Jena
• 2026-08-27: More is different: emergent social conventions and tipping points in AI populations, Ariel Flint Ashery, City St George’s, University of London
• All seminars are 15:00 CET.

More information and coming seminars: https://ri.se/lm-sem

– The Learning Machines Team

This seminar is a collaboration between RISE and Climate AI Nordics – climateainordics.com.

Title: More is different: emergent social conventions and tipping points in AI populations

Speaker: Ariel Flint Ashery, City St George’s, University of London

Abstract: Social conventions are the foundation of social coordination, shaping how individuals come together to form a society. In this talk, I will present theoretical and experimental findings that demonstrate the spontaneous emergence of social norms in LLM populations, as well as the existence of tipping points in social convention. I will show that agentic AI populations can establish social conventions and highlight how collective biases can emerge even when individual agents appear unbiased. I will conclude by stressing how the ability of AI agents to develop norms without explicit programming has significant implications for designing AI systems that align with human values and societal goals.

About the speaker: Ariel Flint is a PhD student in Mathematics at City, University of London. He studies self-organisation in decentralised socio-technical systems, with work on social norms, coordination and cultural evolution. He also has a broader interest in climate-related challenges, including socio-political climate communication and aligning AI systems with climate goals. Previously, he completed a Master's in Theoretical Physics at Imperial College London, and he continues to draw on methods from network science and statistical physics in his current research. His work has been published in Science Advances and has received international media coverage, including features in The Guardian and El País.

Location: This is an online seminar. Connect using Zoom.

Date: 2026-08-27 15:00

Upcoming seminars:

• All seminars are 15:00 CET.

More information and coming seminars: https://ri.se/lm-sem

– The Learning Machines Team

Welcome to the May edition of the Climate AI Nordics Newsletter!

This month’s issue features community updates, job opportunities, and our featured member.

2026 Nordic Workshop on AI for Climate

The 2026 Nordic Workshop on AI for Climate will gather researchers from the Nordics. This one-day, in-person workshop, will take place in Copenhagen, June 26th 2026. The workshop will feature a mix of keynotes, oral presentations, and posters around the topics of AI for tackling climate change, including AI for biodiversity and the green transition. The workshop will be a meeting point for a wide range of researchers from (primarily) around the Nordic countries.

Registration Deadline: June 5th (AoE)

(Read more)

Community spotlight

Featured project: BoquilaHUB - SOTA AI models for biodiversity

BoquilaHUB is an open-source desktop application that makes state-of-the-art AI for biodiversity accessible without complex setup or coding. It enables researchers to efficiently process large-scale camera trap and bioacoustic data using leading models like SpeciesNet and Perch 2. It also supports easy local deployment and shared GPU access, helping democratize AI tools for conservation worldwide.
Read more!

Featured member, May 2026: Alouette van Hove

Alouette van Hove is a PostDoc at the University of Oslo and part of the core team of Climate AI Nordics. Her research focuses on probabilistic experimental design methods for quantifying Arctic methane emissions.
Read more!

News

Remote Sensing Training Course: Satellite and UAV Remote Sensing of the Arctic Biosphere

2026-05-28 Registration is open for the SIOS Remote Sensing Training Course: Satellite and UAV Remote Sensing of the Arctic Biosphere. The course will be held in Longyearbyen, Svalbard from 14 to 19 September.
Read more!

Several climate related workshops at ECCV 2026

2026-05-27 ECCV 2026 in Malmö features as many as 93 workshops, several of which are related to climate and environment and Earth observation, highlighting a growing momentum for environmental applications in computer vision. Climate AI Nordics is proud to co-organize the second edition of the AI for Climate and Conservation (AICC2) workshop as a full-day event. The conference also features two specialized Earth Observation workshops and two additional climate and ecology-focused tracks, bringing together leading global researchers to address urgent planetary challenges.
Read more!

New Strategic Partnership: Climate AI Nordics and Climate Change AI

2026-05-08 Climate AI Nordics (CAIN) is proud to announce a formal partnership with Climate Change AI (CCAI). This collaboration aims to bridge the gap between AI expertise and climate action by facilitating the exchange of knowledge, resources, and joint initiatives between the Nordic region and the global community. By aligning our missions, we seek to accelerate responsible AI-driven solutions for climate mitigation and adaptation.
Read more!

Coming events

More is different: emergent social conventions and tipping points in AI populations

Event date: 2026-06-04.

Webinar with Ariel Flint Ashery, City St George’s, University of London. Social conventions are the foundation of social coordination, shaping how individuals come together to form a society. In this talk, I will present theoretical and experimental findings that demonstrate the spontaneous emergence of social norms in LLM populations, as well as the existence of tipping points in social convention. I will show that agentic AI populations can establish social conventions and highlight how collective biases can emerge even when individual agents appear unbiased. I will conclude by stressing how the ability of AI agents to develop norms without explicit programming has significant implications for designing AI systems that align with human values and societal goals.
Read more!

Climes interdisciplinary summer school 2026

Event date: 2026-06-15.

The Climes Summer School 2026 at Uppsala University offers doctoral, postdoc, and advanced master’s students an interdisciplinary curriculum focused on climate extremes, public health, and societal impacts. The program features a specialized AI component where participants use deep learning and natural language processing to automate the extraction of climate data from texts. While the school is free to attend, applicants must submit their motivation and support letters by March 22nd, 2026, and are generally responsible for their own travel and lodging.
Read more!

2nd Workshop on AI for Climate and Conservation (AICC-2) at ECCV 2026

Event date: 2026-09-08.

Climate AI Nordics is glad to announce that the 2nd Workshop on AI for Climate and Conservation (AICC-) has been accepted at ECCV 2026! The AICC-2 workshop will take place in Malmö, Sweden, Sep 8th or 9th (TBD).
Read more!

HydroImaging: Mining Imaging Data for Hydrological and Environmental Modelling

Event date: 2026-09-13.

Submit your research to HydroImaging, a half-day IEEE ICIP 2026 workshop in Tampere, Finland (September 13–17, 2026). This workshop bridges computer vision, remote sensing, and environmental science to address climate change and the water cycle. Contributions on data-centric ML, multi-modal fusion, and disaster mapping are welcome.
Read more!

Recent events

EarthShift: A new testbed for benchmarking robustnessGeospatial Foundation Models to real-world distribution shifts

This event took place 2026-05-28. Webinar with Kelsey Doerksen, University of Cape Town and Arizona State University. Geospatial Foundation Models claim to offer powerful solutions to simplify and accelerate real-world problems, enabling the capabilities to monitor, analyze, and predict changes on our planet. Current Earth Observation benchmarks to quantify the performance of these models focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. However, when models are deployed, they must generalize to many out-of-distribution scenarios, such as new time periods, geographies, and sensors; and in many contexts, these models are brittle. We introduce EarthShift: the first public testbed for benchmarking robustness across multiple realistic distribution shifts encountered in remote sensing. EarthShift enables users to measure distributional robustness by comparing performance in- and out-of-distribution using datasets from paired data sources, temporal windows, geographic locations, and sensors. EarthShift provides a testbed to guide future work to create foundation models that are robust and reliable in real-world applications.

Read more!

Swedish Climate Symposium

This event took place 2026-05-202026-05-22. The call for abstracts is now open for the Swedish Climate Symposium (Lund, May 20–22, 2026). The event focuses on “Science, Society, and Actions,” connecting researchers with policymakers. If you are applying AI or data science to climate challenges, don’t miss the chance to present your findings. Registration opens in January.

Read more!

Enhanced Flood Detection through Innovative integration of PolSAR, metaheuristic optimization, and deep learning-based segmentation

This event took place 2026-05-07. Webinar with Solmaz Khazaei, KTH Royal Institute of Technology. Flood is the most common natural disaster in the world, and can have catastrophic impacts on human society and the environment, including infrastructure damage, agricultural losses, and casualties, resulting in widespread economic and social disruptions. In early studies, water body detection relied on on-the-spot investigation, hydrological models and common remote sensing techniques that face issues like slow processing and real-time delays. By addressing this challenges we propose a novel hybrid PoLSAR-metaheuristic-DL models and high-resolution remote sensing data to generate accurate and rapid flood mapping for one of the huge recent flood in France. Compared with standard synthetic aperture radars (SAR), polarimetric synthetic aperture radar (PolSAR) is an advanced technique of SAR remote sensing. So, by using polarimetric decomposition methods, features were extracted and feature selection problem, one of the most challenging, was solved by using metaheuristic techniques. The selected features fed into three deep learning-based segmentation models- U_Net_V3, Nested_UNet and Efficient_UNet. The reliability of the generated flood maps was evaluated using Accuracy, precision and recall metrics. Our experimental results indicate that Nested_UNet integrate with optimized PolSAR data achieves the highest segmentation performance, with an accuracy of 0.910, precision of 0.914, and recall of 0.909. These findings underscore the capability of Nested_UNet, demonstrates superior feature extraction abilities, making it a promising choice for real-time flood segmentation applications. Moreover, detecting the knowledge of flooded areas, officials can actively adopt steps to reduce the potential impact of flood, ensure the sustainable management of natural resources and mitigate flood impacts.

View recorded seminar!

Job openings

Postdoctoral Researcher: Satellite Remote Sensing of Carbon Cycle Sources and Sinks

The Finnish Meteorological Institute is seeking a postdoctoral researcher to analyze and exploit satellite remote sensing datasets, including CO₂ and SIF observations, using AI methods for research on the carbon cycle, greenhouse gas emissions, and carbon sinks. This role involves developing advanced methods for data interpretation and source-sink estimation.

Deadline: May 25th, 2026

Read more!

Postdoc in Production Management: AI-driven Sustainability and Resilience

KTH Royal Institute of Technology is seeking a postdoctoral researcher in Production Management to investigate how AI and machine learning can support sustainable and resilient production systems, including circular manufacturing and green industrial transition.

Deadline: June 17th, 2026

Read more!

Postdoc in Modelling, Operation, and Control of Energy Systems – DTU Compute

DTU Compute is seeking a postdoctoral researcher to develop AI-driven solutions for modelling, operating, and controlling sustainable energy systems, focusing on forecasting, optimization, and state estimation for energy production and consumption.

Deadline: May 21st, 2026

Read more!

Postdoc Deep Learning for Image-Based Biodiversity Surveys

NIBIO is seeking a postdoctoral researcher for developing deep learning and computer vision methods to analyze image-based biodiversity surveys, contributing to improved biodiversity monitoring in Europe.

Deadline: May 27th, 2026

Read more!

Machine learning engineer for computer vision and controlled pesticide-use.

Dimensions Agri Technologies (DAT) are recruiting a machine learning engineer. The selected candidate will help reduce and optimize the use of pesticides by developing targeted schemes through machine learning model assisted computer vision.

Deadline: Rolling

Read more!

Your news in the newsletter!

Make sure to share your work with us, by sending us an email ( contact@climateainordics.com), posting in our Slack or some other channel, and we’ll add it to the news feed! Take the chance of showcasing your work or your events to the community!

Also be sure to follow us on LinkedIn and BlueSky. Climate AI Nordics will have the most impact if you repost and like our stories!

Climate AI Nordics is a network of researchers working to harness AI in tackling the climate crisis through both mitigation and adaptation.

We promote the development of AI-based tools and optimization methods that support sustainable decision-making—helping reduce emissions, restore ecosystems, and build climate resilience.

Hi Alouette! Could you tell us a bit about yourself and your work?

I am a postdoctoral researcher at the University of Oslo. I’m part of the ERC-funded ACTIVATE project, where I work on quantifying methane emissions from Arctic landscapes using a combination of machine learning, Bayesian inference, and drone-based field measurements. I am particularly interested in adaptive experimental design – the idea that we can use probabilistic models to actively guide where and when to deploy sensors or fly drones to maximize information value, rather than relying on fixed sampling schemes.

What kinds of research opportunities or collaborations are you excited to be part of in the future?

Methane surface fluxes are highly spatially and temporally variable, yet field data is expensive and sparse — which makes it a compelling problem for both machine learning and experimental design. I’m currently interested in machine learning models that turn sparse ground-based observations into spatially continuous flux maps using landscape and environmental predictors. I am also excited about applying Bayesian experimental design in practice here. The challenge is to develop general sampling policies that remain effective across varying conditions such as landscapes, domain sizes, and weather. I’d love to connect with others working on similar challenges.

Is there anything else you would like to share with the Climate AI Nordics network?

I am looking forward to meeting many members of the network at the Climate AI Nordics workshop in Copenhagen in June (registration is still open)!

What is the best way for people to get in touch with you?

You can best reach out to me by email at a.van.hove@geo.uio.no.

Project website: https://github.com/boquila/boquilahub/

Biodiversity data

A lot of biodiversity monitoring uses methods that produce massive amounts of data. Camera traps, bioacoustics, live cameras, etc. It all can turn into a job that requires people working full-time just going through many files.

Luckily, many innovations in AI have been helpful to automate part of this job. But the software stack is behind; using AI can require many different packages, complicated installations, incompatible versions. It can turn into a nightmare fast.

How BoquilaHUB is solving it

BoquilaHUB is an open-source desktop application that runs on Windows and Linux. You can use it to run AI models for biodiversity use cases like camera trap processing and audio species classification. You can select from many models that are officially supported, or you can bring your own and they can just run (as long as the core architecture is supported).

It currently runs many SOTA models—SpeciesNET, which is state-of-the-art for camera trap species classification; Perch 2, which leads biodiversity audio classification (birds, insects, frogs, mammals, etc); and much more, including even wildlife detection or bug segmentation (useful for counting under the microscope).

On a powerful computer, you could easily process a few terabytes of camera trap data in a single night, with SOTA AI predictions.

The goal

BoquilaHUB wants to democratize access to AI models. It shouldn’t require Python knowledge to run a SOTA model that can be helpful for nature. One of the things we’ve seen from our users, many of them in developing countries, is that it’s not super common to have access to a computer with an Nvidia GPU (that can run AI fast). So we also make it extremely easy to use BoquilaHUB to deploy a REST API endpoint that can allow other users in your local network to use your BoquilaHUB instance. For example, if an office of researchers has only one good computer with a powerful GPU, it’s very easy for that computer to serve SpeciesNet to 20 other computers, everyone just needs to make just a few clicks and it’s done.

What’s next

Ironically, AI predictions can also produce a lot of data, and this new data needs to be managed. BoquilaHUB will be providing tools to manage and understand AI predictions better—edit, transform, visualize, or maybe even automatically sort them with another AI.

Plus, better platform support, better GPU support, and more.

Registration is now open for the SIOS Remote Sensing Training Course 2026 “Satellite and Uncrewed Aerial Vehicle (UAV) Remote Sensing of the Arctic Biosphere” in Svalbard. The course will take place between Monday 14 September and Saturday 19 September 2026 and is open to early career researchers, researchers and technicians from SIOS member institutions and the wider Svalbard and Arctic research community. The application deadline is 17 June.

Webpage with more info and the application form: https://sios-svalbard.org/articles/remote-sensing-training-course-satellite-and-uav-remote-sensing-arctic-biosphere

The complete lineup of 93 workshops for the European Conference on Computer Vision (ECCV 2026) in Malmö, Sweden has been officially announced. Among a massive roster covering foundational machine learning, generative AI, and robotics, there is a clear and inspiring momentum growing around using computer vision and machine learning to address our planet’s most pressing climate and conservation issues.

Out of the total lineup, six standout workshops focus directly on environmental sustainability: two dedicated primarily to Earth Observation (EO) and four dedicated to climate change and ecology.

We are incredibly excited to announce that Climate AI Nordics is organizing AICC2: The 2nd AI for Climate and Conservation Workshop, which has been selected as a prominent full-day event!

Spotlighting Climate & Conservation at ECCV

If you are attending ECCV in Malmö this September, these six workshops features interesting applications of computer vision for planetary health, ecology, and remote sensing.

Our feature event: 2nd Workshop on AI for Climate and Conservation (AICC2)

• Duration: Full-day
• Main organizer: Aleksis Pirinen
• Submission deadline: August 7th
• Learn More: AICC2 ECCV 2026 Website

Building on the success of our inaugural track, AICC2 brings together researchers from machine learning, climate science, and ecology. This full-day workshop will dive into how advanced vision systems can monitor biodiversity loss, model climate risk, and optimize mitigation strategies. We invite the global community to join us in Malmö to push the boundaries of what climate AI can achieve.

Complementary climate & ecology tracks

Alongside AICC2, three other crucial half-day and full-day workshops focus heavily on biodiversity and natural resources:

• 2nd Workshop on Marine Vision (Full-day) Main organizer: Malte Pedersen Highlighting the critical need for automated computer vision solutions to overcome the unique physical and visual challenges of underwater imaging, enabling researchers to efficiently monitor and protect rapidly degrading marine ecosystems. Website: https://vap.aau.dk/marinevision/

• CVNH – Computer vision for natural heritage (Half-day)
  Main organizer: Juan Miguel Valverde
  Focusing on the preservation, documentation, and automated monitoring of vulnerable natural landmarks and ecosystem heritages worldwide. Website: https://computer-vision-for-natural-heritage.github.io/

• 3rd workshop on computer vision for ecology (Full-day)
  Main organizer: Julia Chae
  An vital forum focused on species identification, animal tracking, and behavioral analysis in the wild to support ecological research and anti-poaching efforts. Website: https://cv4e-workshop.github.io/

Earth observation-centric workshops

For those working with satellite imagery and geospatial data streams, two dedicated workshops cover the infrastructure and models needed to sense planetary changes at scale:

• TerraBytes II: Towards global datasets and models for Earth observation (Full-day)
  Main organizer: Mikolaj Czerkawski
  Addressing the challenges of scaling up vision models to ingest, process, and accurately interpret global-scale satellite and remote sensing datasets. Website: https://terrabytes-workshop.github.io/

• GAIA 2026: Geospatial AI and foundation models (Half-day)
  Main organizer: Danda Paudel
  Exploring how modern foundation models can be adapted to spatial, geographic, and temporal dimensions for land-use mapping and environmental prediction.

Event Details:
ECCV 2026 Workshops
September 8–9, 2026 Malmö, Sweden

As computer vision transitions from synthetic benchmarks to real-world applications, these workshops represent a vital bridge to mitigate and adapt to the climate crisis. We look forward to seeing you in Malmö this September to collaborate, share research, and expand the impact of Climate AI Nordics. Stay tuned for call-for-papers deadlines and speaker announcements!

Full list

https://eccv.ecva.net/Conferences/2026/Workshops

More info

https://eccv.ecva.net/

Call for Participation is open at the AICC-2 webpage!

Background

The climate crisis is one of our greatest challenges, requiring urgent breakthroughs in both mitigation and adaptation. While the conservation of natural carbon stocks and biodiversity hotspots is critical, adapting to inevitable climate shifts requires robust predictive modeling and real-time monitoring. AI, including Computer Vision, is uniquely positioned to address these needs through advanced spatiotemporal analysis, multimodal sensor fusion, and automated semantic understanding of our planet’s surface.

AICC-2 will bridge the gap between fundamental AI research and high-impact environmental applications. Beyond immediate societal benefits, tackling climate-related data offers the AI & Computer Vision community a rich set of research avenues that transcend standard benchmarks. These include e.g. (i) domain generalization across seasonal, topographical, and sensor-induced distribution shifts; (ii) learning from imperfect data, e.g. fine-grained categorization in long-tailed or noisy crowd-sourced datasets; (iii) large-scale change detection via self-supervised learning on satellite and aerial streams.

AICC-2 will focus on identifying open problems in climate & conservation and highlighting cases where AI & CV has moved from theoretical proof-of-concept to field-deployed impact. By uniting domain scientists and AI/CV researchers, we aim to inspire the community to tackle these high-dimensional, multi-scale challenges.

The program will be guided by the these questions:

What are the open problems in climate and conservation?

How can AI & CV researchers help practitioners make better decisions?

How can the AI & CV communities benefit from tackling domain-specific problems?

Speakers

• Devis Tuia (EPFL)
• Bruno Sanchez-Andrade Nuño (LGND)
• Nora Gourmelon (Friedrich-Alexander University of Erlangen–Nuremberg)
• Abdulhakim Abdi (Lund University)

Organizers

• Aleksis Pirinen (RISE Research Institutes of Sweden)
• Ankit Kariryaa (University of Copenhagen)
• Begüm Demir (TU Berlin)
• Nico Lang (University of Copenhagen)
• Olof Mogren (RISE)
• Isabelle Tingzon (RISE & KTH Royal Insitute of Technology)
• Lucia Gordon (Harvard University)
• Joakim B. Haurum (University of Southern Denmark)

Read more at the AICC-2 webpage