Climate AI Nordics

Climate AI Nordics

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

SWEO2025: Earth observation event in Stockholm

Event date: 2025-10-23

Event location: Solna, Stockholm

SWEO2025 is an event that revolves around the practical applications of Earth observation data, including within environmental monitoring and similar areas. The main organizer of SWEO2025 is the Swedish National Space Agency, in collaboration with Technical University of Luleå, RISE and AI Sweden.

The event may be of interest to a broad range of actors in academia, industry and beyond.

SWEO2025 takes place in Solna, Stockholm, between October 23rd and 24th. Click here for registration to the event.

This event is not co-organized by or affiliated with Climate AI Nordics. More info (in Swedish): www.rymdstyrelsen.se/rymddata/sweo2025/

Published:

Categories:

You May Also Enjoy

Self-supervised pre-training for glacier calving front extraction from synthetic aperture radar imagery

Event date:

Webinar with Nora Gourmelon, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). The factors influencing melt at glacier fronts facing the ocean remain an active area of research. To better understand these factors, it is essential to monitor changes in glacier calving fronts. Due to the importance of weather-dependent and seasonal variations, Synthetic Aperture Radar (SAR) is the preferred imaging method for such monitoring. In recent years, deep learning models have been developed to automate the extraction of calving front positions, however, their performance on SAR data remains suboptimal. Limited labeled data and high variability in SAR images hinder traditional supervised learning. Foundation models pre-trained on large, diverse datasets could provide robust feature representations that require minimal labeled data for fine-tuning on specific SAR tasks. However, in preliminary experiments, we found that the domain gap is too large for the task of extracting calving fronts from SAR imagery, and foundation models fine-tuned on the "CAlving Fronts and where to Find thEm" (CaFFe) benchmark dataset performed subpar. Therefore, we compiled an unlabeled dataset of Sentinel-1 SAR image sequences of Arctic glaciers, each associated with a single Sentinel-2 optical reference image. Using this dataset, we developed a novel multi-modal self-supervised pre-training strategy and applied it to pre-train a hybrid CNN-transformer model. Fine-tuning on the CaFFe benchmark showed that the pre-trained model outperforms its non-pre-trained counterpart, enabling more robust calving front segmentation and demonstrating the potential of data-efficient learning for SAR imagery.

Featured member, August 2025: Miki Verma

Published:

Miki is the Lead Data Scientist at Rewiring America, the leading U.S. nonprofit dedicated to the electrification of American homes. He develops data-driven tools, research, policy, and narratives to help facilitate households' transition from fossil-fuel-powered to efficient electric systems. His recent work includes leading the development of the Residential Electrification Model, a free API that predicts bill savings, emissions reductions, and energy impacts of electrification upgrades at any U.S. address.

Generative domain adaptation and foundation models for robust Earth observation

Event date:

Webinar with Georges Le Bellier, Conservatoire National des Arts et Métiers. Deep learning for remote sensing plays a crucial role in turning satellite and aerial imagery into dependable, real-world insights. However, Earth observation models must handle diverse environments, sensors, and conditions—such as clouds, seasonal shifts, and geographic differences—while still producing accurate results. In this talk, we explore two paths that lead to more robust and adaptable algorithms: generative domain adaptation and geospatial foundation models. First, I will introduce FlowEO, a generative approach of Unsupervised Domain Adaptation (UDA) for Earth observation, and show its high performance in UDA scenarios for several downstream tasks, including dense prediction and classification. This flow-matching-based translation method improves pretrained predictive models' accuracies in challenging scenarios such as post-disaster response and high cloud coverage cases with SAR-to-optical translation. FlowEO’s generative domain adaptation method is independent of the downstream task and does not require retraining the predictive model. Then, I will present “PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models“, a standardized evaluation protocol that covers a diverse set of datasets, dense prediction tasks, resolutions, sensor modalities, and temporalities. This benchmark includes comparison between geospatial foundation models but also with supervised baselines, namely U-Net and ViT, and highlights the strengths and weaknesses of GFMs. In addition, PANGAEA evaluates models’ accuracy in cases where labels are limited and questions the impact of multi-temporal data for GFMs.

ESA Phi-Lab Sweden Opening Event

Event date:

Welcome to the official opening of ESA Phi-Lab Sweden in Stockholm. The opening ceremony will take place on August 26, starting with a presentation of the Phi-Lab’s mission and thematic focus, followed by a symbolic ribbon-cutting ceremony. After a light lunch, the afternoon continues with a conference programme featuring inspiring presentations, forward-looking discussions, and a poster session for sharing contributions (pre-registration required). We welcome researchers, start-ups, industry players and the public sector to join this important step towards a future where Sweden plays an active role in shaping AI-driven space applications.