5th ECMWF-ESA Machine Learning Workshop

Download Programme
The times below are displayed for Europe/London. We have detected that you are visiting us from .

Please select a timezone to show adjusted event times accordingly.



Location: Botte B4 pavilion - DAMA Technopole

Agenda time displays according to the selected time zone.

Monday, 13 April 2026 Speaker(s)
Opening and keynote
Session chairs: Massimo Bonavita (ECMWF) and Rochelle Schneider (ESA)
12:00 – 13:00 Registration and coffee
13:00 – 13:10 Opening and welcome
Video recording
Massimo Bonavita (ECMWF)
Rochelle Schneider (ESA)
13:10 – 13:40 AI for Humanity: Foundational Machine Learning and Data Assimilation for a Resilient Earth

Keynote speaker


Presentation slides
Video recording
Rossella Arcucci (Imperial College London)
13:40 – 14:10 Machine learning–driven advances in geophysical data assimilation

Keynote speaker


Presentation slides
Video recording
Marc Bocquet (École Nationale des Ponts et Chaussées and ECMWF Fellow)
14:10 – 17:10 Poster session and ice breaker
14:10 – 15:10 Coffee and posters
15:10 – 17:10 Aperitivo cocktail reception and posters
Aperitivo sponsored by the University of Bologna, the Alma Climate Institute




Location: Botte B4 pavilion - DAMA Technopole

Agenda time displays according to the selected time zone.

Tuesday, 14 April 2026 Speaker(s)
Session 1.1: TA1 ML4DTE system

Session chairs: Rochelle Schneider (ESA) and Mounia El Baz (ESA)

08:00 – 08:30 CLIM4health: from Citizen Science, Machine Learning and Earth Observation towards Urban Climate Services

Keynote speaker


Presentation slides
Video recording
Ana Oliveira (CoLAB +ATLANTIC)
08:30 – 08:50 The WeatherGenerator Project: Building a multi-modal, multi-resolution Foundation Model for Weather and Climate science
Presentation slides
Video recording
Ilaria Luise (ECMWF)
08:50 – 09:10 Lessons from Weather: Adapting GraphCast for Global Ocean Forecasting
Presentation slides
Video recording
Stefano Campanella (National Institute of Oceanography and Applied Geophysics - OGS, University of Trieste)
09:10 – 09:30 High-Resolution Thermal Mapping for Land Cover Intervention Planning
Presentation slides
Video recording
Hugo Poupard (Murmuration-SAS)
09:30 – 09:50 Bris and Forecast-in-a-Box: Applications and results for Malawi.
Presentation slides
Video recording
Lene Østvand (The Norwegian Meteorological Institute)
09:50 – 10:20 Group photo and coffee break
Session 1.2: TA1 ML4DTE system
Session chairs: Rochelle Schneider (ESA) and Mounia El Baz (ESA)
10:20 – 10:40 Probing sensitivities in sea ice surrogate models toward probabilistic forecasting
Presentation slides
Video recording
Flavia Porro (University of Bologna)
10:40 – 11:00 Downscaling of vertical profiles of mean and turbulent atmospheric variables using deep learning
Presentation slides
Video recording
Maximilian Pierzyna (Technische Universiteit Delft)
11:20 – 11:40 Generative Adversarial Networks for Simulating Dynamic Interactions in Digital Twins of Coastal Ecosystems

Online presentation


Presentation slides
Video recording
Oscar Leung (HKU)
Ye Ha Kim (UCL)
11:00 – 11:20 AI Climate Emulators as Tools for Reducing Weather Risk Uncertainty: Insights from a Large-Ensemble Approach
Presentation slides
Video recording
Amaury Lancelin (Laboratoire de Météorologie Dynamique (LMD), Ecole Normale Supérieure, RTE)
11:40 – 12:00 Going with the flow: generalising physically consistent data-driven sea-ice models
Presentation slides
Video recording
Tobias Finn (CEREA, ENPC, EDF R&D, Institut Polytechnique de Paris)
12:00 – 13:30 Lunch break
Session 1.3: TA1 ML4DTE system
Session chairs: Rochelle Schneider (ESA) and Mounia El Baz (ESA)
13:30 – 13:50 A New Concept for Comparing Satellite Observations and km-scale Atmospheric Simulations using Self-Supervised Machine Learning
Presentation slides
Video recording
Dwaipayan Chatterjee (Institute for Meteorology and Climate Research, Karlsruhe Institute for Technology)
13:50 – 14:10 SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation
Presentation slides
Video recording
Joppe Massant (Ghent University)
14:10 – 14:30 Evaluation of GraphCast and PanguWeather over India and Downscaling using WRF for Simulating the 2023 North Indian Floods

Online presentation


Presentation slides
Balu Shaharica (Indian Institute of Technology Roorkee)
14:30 – 15:10 TA1 - Open discussion
Video recording
15:10 – 15:40 Coffee break
Session 2.1: TA2 Hybrid ML-Physics based systems for DA and Weather and Climate prediction
Session chairs: Rossella Arcucci (Imperial College) and Marc Bocquet (ENPC)
15:40 – 16:00 Advancing Global Weather Prediction at ECCC Using Spectral-Nudging-Based Hybrid NWP-MLWP Modelling
Presentation slides
Video recording
Leo Separovic (Environment and Climate Change Canada)
16:00 – 16:20 Hybrid NWP-AI at Météo-France : nudging AIFS large scales in the global NWP operational model ARPEGE
Presentation slides
Video recording
Vincent Chabot (Météo France)
16:20 – 16:40 Enhanced land surface data exploitation using machine learning
Presentation slides
Video recording
Patricia de Rosnay (ECMWF)

Location: Botte B4 pavilion - DAMA Technopole

Agenda time displays according to the selected time zone.

Wednesday, 15 April 2026 Speaker(s)
Session 2.2:
Session chairs: Rossella Arcucci (Imperial College) and Marcin Chrust (ECMWF)
08:00 – 08:30 Data Assimilation in the era of the AI revolution - where we stand today

Keynote speaker


Presentation slides
Video recording
Steve Penny (Sofar Ocean)
08:30 – 08:50 Development of an offline and online hybrid model for the Integrated Forecasting System
Presentation slides
Video recording
Alban Farchi (ECMWF)
08:50 – 09:10 Online bias-correction in sea-ice models using machine learning and data assimilation
Presentation slides
Video recording
Giovanni De Cillis (Dept. of Physics and Astronomy “Augusto Righi”, University of Bologna, Bologna, Italy)
09:10 – 09:30 RUSH: Rapid-Update High-Resolution precipitation nowcasting and Global AI/NWP downscaling in a single Latent-Diffusion model
Presentation slides
Video recording
Simon De Kock (Electronics and Informatics (ETRO), Vrije Universiteit Brussel & Royal Meteorological Institute of Belgium)
09:30 – 10:00 Coffee break
Session 2.3: TA2
Session chairs: Rossella Arcucci (Imperial College) and Marcin Chrust (ECMWF)
10:00 – 10:20 Hybrid machine learning and ensemble data assimilation
Presentation slides
Video recording
Wei Pan (ECMWF)
10:20 – 10:40 Machine Learning-Driven Background Error Covariances for High-Resolution Data Assimilation
Presentation slides
Video recording
Ravi Shankar Nemani (School of Mathematical, Physical & CompUniversity of Reading and National Centre for Earth Observation)
10:40 – 11:00 Multi-hazard nowcasting system over Romania

Online presentation


Presentation slides
Video recording
Claudiu Adam (National Meteorological Administration)
11:00 – 11:20 Unmasking Compensating Biases: A Process-Partitioned Neural Network Approach
Presentation slides
Video recording
Yuiko Ichikawa (University of Cambridge)
11:20 – 12:00 TA2 - Open discussion
Video recording
12:00 – 13:30 Lunch
Session 3.1: TA3 ML applications for Earth system observations
Session chairs: Maryam Pourshamsi (ESA) and Chiara Maria Cocchiara (ESA)
13:30 – 14:00 Harnessing Satellite Data and AI to Address Climate Hazards for Children

Keynote speaker


Presentation slides
Video recording
Do-hung Kim (UNICEF)
14:00 – 14:20 Collaborative Labelling of Earth System Features in Satellite Data for Nowcasting and Climate Applications
Presentation slides
Video recording
Lauren Biermann (EUMETSAT)
14:20 – 14:40 Machine-learning-based observation operators for land-surface data assimilation
Presentation slides
Video recording
Peter Weston (ECMWF)
14:40 – 15:00 A data-driven reanalysis of Amazon water levels with deep learning
Presentation slides
Video recording
Ruben Cartuyvels (ESA)
15:00 – 15:30 Coffee break
Session 3.2: TA3
Session chairs: Maryam Pourshamsi (ESA) and Chiara Maria Cocchiara (ESA)
15:30 – 15:50 Benchmarking Earth Observation embeddings for large scale aboveground biomass mapping
Presentation slides
Video recording
Yu-Feng Ho (OpenGeoHub)
15:50 – 16:10 Contrail Instance Segmentation on Geostationary Imagery
Presentation slides
Video recording
Ana Maria Pelin (EUROCONTROL & TU Delft)
16:10 – 16:30 GridShield™: A Hybrid ML-Satellite Fusion Framework for Real-Time Power Grid Resilience and Climate-Verified Carbon Credit Generation Using ESA Copernicus Sentinel Data

Online presentation

Milagrosa Russelle Ballestar (iONTEK Power Solutions Corporation - Innovate with EU Space Data Mentoring Programme 2025)
16:30 – 16:50 Data-Driven Eddy Detection from Wide-Swath Altimetry
Presentation slides
Video recording
Matteo Broccoli (CMCC Foundation, Italy)
16:50 – 17:10 Developing a Multimodal AI Framework for Wetlands Mapping with Multi-Sensor Earth Observation Data

Online presentation


Presentation slides
Video recording
Khunsa Fatima (University of Leicester)

Location: Botte B4 pavilion - DAMA Technopole

Agenda time displays according to the selected time zone.

Thursday, 16 April 2026 Speaker(s)
Session 3.3: TA3
Session chairs: Maryam Pourshamsi (ESA) and Chiara Maria Cocchiara (ESA)
08:00 – 08:20 From Synthetic to Real: A Scalable Dataset and ML Framework for Global Methane Monitoring
Presentation slides
Video recording
Enno Tiemann (OHB Digital Connect / Technical University of Munich (TUM))
08:20 – 08:40 Filling the Multisensor Gap: Multimodal Generative Models for Volcano Monitoring
Presentation slides
Video recording
Simona Cariello (INGV-OE Istituto Nazionale di Geofisica e Vulcanologia Osservatorio Etneo, Catania, Italia)
08:40 – 09:00 Deep learning emulation of the far-infrared fast forward operator for ESA FORUM satellite
Presentation slides
Video recording
Simone Raciti (University of Bologna)
09:00 – 09:20 Intelligent All-sky Cameras for Dense Mesoscale Observations

Online presentation


Presentation slides
Video recording
Ben Pickering (Wx Labs Ltd and NCAS)
09:20 – 10:00 TA3 - Open discussion
Video recording
10:00 – 10:20 Coffee break
Session 4.1: TA4 End-to-end ML systems for DA and Weather and Climate Prediction Multidomain ML4ESOP
Session chairs: Alberto Carrassi (UniBo) and Massimo Bonavita (ECMWF)
10:20 – 10:40 GraphDOP: Are observations all you need?
Presentation slides
Video recording
Eulalie Boucher (ECMWF)
10:40 – 11:00 An End-to-End Observation-Centric Graph Neural Network Framework for Global Earth System Prediction
Presentation slides
Video recording
Azadeh Gholoubi (NOAA/NWS/NCEP/EMC)
11:00 – 11:20 Duo-AttnOPNets: An End-to-End ML–4D-Var Framework for Atmospheric Composition Forecasting and Data Assimilation
Presentation slides
Video recording
Judongyang Zhou (Imperial College London)
11:20 – 11:40 Extending the Aila AI Weather Model: A Multi-Decoder Approach for Variable Expansion
Presentation slides
Video recording
Mikko Partio (Finnish Meteorological Institute)
11:40 – 12:00 AI-Based Weather Forecasting for Switzerland
Presentation slides
Video recording
Claire Merker (MeteoSwiss)
12:00 – 13:30 Lunch break
Session 4.2: TA4
Session chairs: Alberto Carrassi (UniBo) and Massimo Bonavita (ECMWF)
13:30 – 14:00 From Real-Time Big Data Assimilation on Fugaku to Synergistic Development of DA and AI: Osaka Expo 2025 and Beyond

Keynote speaker


Presentation slides
Video recording
Takemasa Miyoshi (RIKEN)
14:00 – 14:20 Beyond the atmosphere: Building a Data-Driven Earth System Model at ECMWF
Presentation slides
Video recording
Nina Raoult (ECMWF)
14:20 – 14:40 The physics of AI weather models
Presentation slides
Video recording
George Craig (Meteorological Institute, LMU Munich)
14:40 – 15:00 Interpretability of AI Weather Models via Intermediate Decoding
Presentation slides
Video recording
Matthias Beylich (Meteorological Institute, LMU Munich)
15:00 – 15:30 Coffee break
Session 4.3: TA4
Session chair: Massimo Bonavita (ECMWF)
15:30 – 15:50 Leveraging the kilometre-scale AROME reanalysis to develop AI-based regional forecasting systems over Western Europe
Presentation slides
Video recording
Thomas Rieutord (Météo-France)
15:50 – 16:10 Probabilistic GAN for European Winter Storm Downscaling
Presentation slides
Video recording
Athul Rasheeda Satheesh (Karlsruhe Institute of Technology)
16:10 – 16:30 Towards few-sample extreme event likelihoods with guided diffusion models
Presentation slides
Video recording
Peter Manshausen (NVIDIA)
16:30 – 17:00 TA4 - Open discussion
Video recording

Location: Botte B4 pavilion - DAMA Technopole

Agenda time displays according to the selected time zone.

Friday, 17 April 2026 Speaker(s)
Session 5.1: TA5 - HP and new computing technologies for ML applications in ESOP
Session chair: Nina Raoult (ECMWF) and Diego Jatoba Dos Santos (ESA)
08:00 – 08:30 Combining HPC and AI to advance potential: Example from HLRS and HammerHAI

Keynote speaker

Online presentation


Presentation slides
Video recording
Bastian Koller (High Performance Computing Center Stuttgart)
08:30 – 08:50 Scalable GPU-Accelerated Training of Graph Neural Networks for High-Resolution ESOP Simulations

Online presentation


Presentation slides
Video recording
Oscar Leung (HKU)
Ye Ha Kim (UCL)
08:50 – 09:10 Improving the performance and scalability of Anemoi
Presentation slides
Video recording
Jan Polster (ECMWF)
09:10 – 09:30 Satellite Earth Observation and AI–QC-Physics methods for enhanced climate predictions and volcano–climate interaction modeling
Presentation slides
Video recording
Eleonora Amato (Istituto Nazionale di Geofisica e Vulcanologia (INGV), Sezione Osservatorio Etneo, Catania, Italy)
09:30 – 10:00 Coffee break
Session 5.2: TA5
Session chair: Nina Raoult (ECMWF) and Diego Jatoba Dos Santos (ESA)
10:00 – 10:20 Optimising Anemoi for higher resolution data and next-generation systems
Presentation slides
Video recording
Cathal O Brien (ECMWF)
10:20 – 10:40 Global Volcano Monitoring from Space with hybrid Quantum Convolutional Neural Networks
Presentation slides
Video recording
Federica Torrisi (INGV-OE Istituto Nazionale di Geofisica e Vulcanologia Osservatorio Etneo, Catania, Italia)
10:40 – 11:00 Profiling Machine Learning Weather-Forecasting Models in Anemoi
Presentation slides
Video recording
Marieke Plesske (HPC Applications Team)
11:00 – 11:30 TA5 - Open discussion
Video recording
11:30 – 11:40 Closing remarks
Video recording
Massimo Bonavita (ECMWF)
Rochelle Schneider (ESA)