Aims and Scopes:

The vast amount of data currently produced by modern Earth Observation (EO) missions and measurements on the surface has raised new challenges for the Remote Sensing Community and atmospheric modellers. EO sensors can now offer (very) high spatial resolution images with revisit time frequencies never achieved before considering different signals, e.g., multi-(hyper)spectral optical, radar, LiDAR, and Digital Surface Models. 

On the other hand, atmospheric composition and processes are measured on the surface, starting from molecular scale measurements with mass spectrometers, particle counters, and more traditional meteorological instruments. Modern machine learning techniques can be crucial in dealing with such heterogeneous, multi-scale, and multi-modal data.

Some methods gaining attention in this domain include deep learning, domain adaptation, semi-supervised approach, time series analysis, active learning, explainable artificial intelligence, uncertainty quantification, and interactive model building and visualisation. Even though machine learning and the development of ad-hoc techniques are gaining popularity, we still see a significant need for more interaction between domain experts and machine learning researchers. 

This workshop aims to be an international forum where machine learning researchers and domain experts can meet each other to exchange, debate, and draw short and long-term research objectives around the exploitation and analysis of EO and atmospheric data via Machine Learning techniques. Among the workshop’s goals, we want to give an overview of the current machine-learning research dealing with EO and other atmospheric measurement data. On the other hand, we want to stimulate concrete discussions to pave the way to new machine learning frameworks especially tailored to deal with such data.

Topics

The non-exclusive list of topics for the workshop includes, to the extent related to the EO procesess: 

• Supervised Classification of Multi(Hyper)-spectral data

• Supervised Classification of Satellite Image Time Series data

• Unsupervised Learning of EO Data

• Deep Learning approaches to deal with EO Data

• Machine Learning approaches for the analysis of multi-scale EO Data

• Machine Learning approaches for the analysis of multi-source EO Data

• Semi-supervised classification approaches for EO Data

• Active learning for EO Data

• Transfer Learning and Domain Adaptation for EO Data

• Interpretability and explainability of machine learning methods in the context of EO data analysis

• Bayesian machine learning for EO Data

• Dimensionality Reduction and Feature Selection for EO Data

• Graphicals models for EO Data

• Structured output learning for EO Data

• Multiple instance learning for EO Data

• Multi-task learning for EO Data

• Online learning for EO Data

• Embedding and Latent factor for EO Data

• Foundation Models for Earth Observation

• Multi-Modal approaches for EO Data

• Self-supervised learning for EO Data

• Physics-informed machine learning for EO Data

The workshop will be held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD) which will be held in Porto, Portugal from the 7th to the 11th of September 2026 (official website : https://ecmlpkdd.org/2026/). The workshop is sponsored by ESA (European Space Agency), the AFRIF (The French Association of Pattern Recognition and Interpretation), the GdR MADICS (Masses de Données, Informations et Connaissances en Sciences) and the EGC (Association Internationale Francophone d'Extraction et de Gestion des Connaissances).