Climate AI Nordics

Climate AI Nordics

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

Workshop on Advances in Representation Learning for Earth Observation (REO) at EurIPS 2025

Event date: 2025-12-06

Event location: Bella Center, Copenhagen

The REO workshop will take place in Copenhagen, Denmark, Dec 6th or 7th (TBD; workshops are co-located with EurIPS)!

Call for Participation is open at the REO webpage (Submission deadline Oct. 15)!

Background

The Representation Learning for Earth Observation (REO) workshop brings together researchers and practitioners from machine learning, computer vision, and Earth sciences to advance the development of robust, interpretable, and scalable models for monitoring our planet. With the growing availability of large-scale, multimodal Earth observation (EO) data and the rise of general-purpose foundation models, new opportunities and challenges emerge for integrating data-driven approaches across sensing modalities and application domains. REO will provide a forum for presenting novel technical methods, scientific applications, and system-level innovations, fostering cross-disciplinary exchange and collaborations between academia, industry, and policy stakeholders.

Due to EO’s huge potential to tackle pressing societal challenges, there has also been a growing interest from the machine learning and computer vision community in recent years. The development of representation learning approaches within the EO domain has gained interest and momentum beyond academia. Notable recent examples include Google DeepMind’s AlphaEarth, IBM’s Terramind, AllenAI’s Earth System, and Meta’s DINOv3.

This growing interest calls for increased community exchange around the development, deployment, and the practical use of these models. This workshop aims to discuss the following :

  • Where are we, and how can we move forward as a community?
  • What are the open challenges in learning representations of EO data?
  • In the era of general-purpose one-for-all models, what is the role of specialized approaches?

Speakers

  • Gustau Camps (Universitat de València)
  • Michal Kazmierski (Google DeepMind)
  • Julia Gottfriedsen (OroraTech)
  • Bertrand Le Saux (European Comission)
  • Ankit Kariryaa (University of Copenhagen)

Organizers

  • Loic Landrieu (ENPC)
  • Begüm Demir (BIFOLD and TU Berlin)
  • Nico Lang (University of Copenhagen, Pioneer Centre for AI)
  • Johannes Jakubik (IBM)
  • Valerio Marsocci (ESA, Φ-lab)
  • Ruben Cartuyvels (ESA, Φ-lab)
  • Hui Zhang (University of Copenhagen)

Read more at the REO webpage

Published:

Categories:

You May Also Enjoy

Earth observation and deep learning for urban applications

Event date:

Webinar with Sebastian Hafner, RISE. Urbanization is progressing at an unprecedented rate in many places around the world, making Earth observation (EO) a vital tool for monitoring its dynamics on a global scale. Modern satellite missions provide new opportunities for urban mapping and change detection (CD) through high-resolution imagery. At the same time, EO data analysis has advanced from traditional machine learning approaches to deep learning (DL), particularly Convolutional Neural Networks (ConvNets). Yet, current DL methods for urban mapping and CD face key challenges, including effectively integrating multi-modal EO data, reducing reliance on large labeled datasets, and improving transferability across geographic regions. This talk will present methods to address these challenges in urban mapping and CD, with applications such as multi-hazard building damage detection. It will also highlight the IDEAMAPS Data Ecosystem project, showing how its community-centric approach advances our understanding of urban deprivation and enables DL-based deprivation mapping.

Generative domain adaptation and foundation models for robust Earth observation

Event date:

Webinar with Georges Le Bellier, CNAM. 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.

Debiasing AI predictions for causal inference without fresh ground truth data

Event date:

Webinar with Markus Pettersson, Chalmers University of Technology. Machine learning models trained on Earth observation data, particularly satellite imagery, have recently shown impressive performance in predicting household-level wealth indices, potentially addressing chronic data scarcity in global development research. While these predictions exhibit strong predictive power, they inherently suffer from shrinkage toward the mean, resulting in attenuated estimates of causal treatment effects and thus limiting their utility in policy evaluations. Existing debiasing methods, such as Prediction-Powered Inference (PPI), require additional fresh ground-truth data at the downstream causal inference stage, severely restricting their applicability in data-poor environments. In this paper, we introduce and rigorously evaluate two novel correction methods—linear calibration correction and Tweedie's correction—that substantially reduce prediction bias without relying on newly collected labeled data. Our methods operate on out-of-sample predictions from pre-trained models, treating these models as black-box functions. Linear calibration corrects bias through a straightforward linear transformation derived from held-out calibration data, while Tweedie's correction leverages empirical Bayes principles to directly address shrinkage-induced biases by exploiting score functions derived from predicted outcomes. Through analytical exercises and experiments using Demographic and Health Survey (DHS) data, we demonstrate that both proposed methods outperform existing data-free approaches, can achieve significant reductions in attenuation bias and thus providing more accurate, actionable, and policy-relevant estimates. Our approach represents a generalizable, lightweight toolkit that enhances the reliability of causal inference when direct outcome measures are limited or unavailable.

Postdoc in Climate Extremes & Population Health

Published:

Uppsala University’s CLIMES centre is hiring a postdoc to study the impacts of climate extremes (heatwaves, floods, droughts) on population health, with a focus on vulnerable groups.