24–26 August 2026 · Bonn, Germany
Workshop on Machine Learning for Earth System Modelling
About the Workshop
We are pleased to announce the fourth Workshop on Machine Learning for Earth System Modelling, following a series of three successful workshops. The workshop brings together leading researchers working on large-scale machine learning approaches for weather and climate science. It will take place in Bonn, Germany, and follows the Hackathon on Machine Learning for the Earth System.
The workshop will take place on August 24 – 26, 2026 in the Universitätsclub Bonn, Germany.
Registration and abstract submission will open soon
The event brings together researchers from Earth system science, mathematics, and computational science to discuss recent advances in machine learning for weather and climate applications.
Topics include:
- Machine learning-based numerical weather prediction
- Climate emulators and machine learning-based climate models
- Machine learning-based Earth system component models (e.g. ocean and land models)
- Incorporation of Earth system observations into ML models
- Evaluation and explainability of machine learning models
- Datasets for model training, evaluation, and benchmarking
Read about our workshop last years, 2025 and 2024.
Timeline, Important Dates & Abstract Submissions
Workshop Registration opens: tba
Workshop dates: 24–26 August 2026
Abstract submission opens: tba
Notification of accepted abstracts: 22 June 2026
Abstract submission
We invite you to submit your abstracts with relevance to the topics to be discussed in this year’s workshop.
Submissions will only be via CMT* platform (https://cmt3.research.microsoft.com/About)
Authors will need to create an account on the platform (if they do not already have one) at: https://cmt3.research.microsoft.com/docs/help/general/account-creation.html
Each abstract should be a maximum of 1 page.
Notification of accepted abstracts will be communicated on 30 Jun 2026.
MLESM Hackathon
The workshop follows the Hackathon on Machine Learning for the Earth System on 19-21 August 2026 in Bonn. Please find more information on how to apply here:
Workshop Registration
On-site participation will cost 260 €, including access to the venue, coffee breaks, lunches, and a conference dinner.
Up to 30 student seats are available at a reduced rate of 150 € (proof of student status required).
Online participation will cost 75 €.
Registration will open soon.
Local Organising Committee
Important Information
Information about the workshop for all registered participants will be sent via mlesm-workshop@cesoc.net or mlesm-registrations@cesoc.net. Please make sure to mark them as safe, i.e., not spam/junk.No time to attend our MLESM event but interested anyway, stay tuned and subscribe at mlesm-workshop@listen.uni-bonn.de.
For questions please contact us via email: mlesm-workshop@cesoc.net
Supported by
We gratefully acknowledge the support by CESOC, ECMWF, the TRA Modelling at the University of Bonn, the Forschungszentrum Jülich and the University of Cologne.
Acknowledgement: The Microsoft CMT service will be used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
Programme
(tba)
Alternative Layouts mit komprimiertern Tabs
24–26 August 2026 · Bonn, Germany
24–26 August 2026 · Bonn, Germany
Workshop on Machine Learning for Earth System Modelling
The fourth Workshop on Machine Learning for Earth System Modelling brings together leading researchers working on large-scale machine learning approaches for weather and climate science.
About the MLESM Workshop
We are pleased to announce the fourth Workshop on Machine Learning for Earth System Modelling, following a series of three successful workshops. The workshop will take place in Bonn, Germany, and follows the Hackathon on Machine Learning for the Earth System.
The workshop will take place on August 24 – 26, 2026 in the Universitätsclub Bonn, Germany.
Registration and abstract submission will open soon
The event brings together researchers from Earth system science, mathematics, and computational science to discuss recent advances in machine learning for weather and climate applications.
Topics include:
- Machine learning-based numerical weather prediction
- Climate emulators and machine learning-based climate models
- Machine learning-based Earth system component models (e.g. ocean and land models)
- Incorporation of Earth system observations into ML models
- Evaluation and explainability of machine learning models
- Datasets for model training, evaluation, and benchmarking
Read about our workshop last years, 2025 and 2024.
Workshop Registration
On-site participation will cost 260 €, including access to the venue, coffee breaks, lunches, and a conference dinner.
Up to 30 student seats are available at a reduced rate of 150 € (proof of student status required).
Online participation will cost 75 €.
Registration will open soon.
Timeline & Abstract Submissions
Workshop Registration opens: tba
Workshop dates: 24–26 August 2026
Abstract submission opens: tba
Notification of accepted abstracts: 22 June 2026
We invite you to submit your abstracts with relevance to the topics to be discussed in this year’s workshop.
Submissions will only be via CMT* platform (https://cmt3.research.microsoft.com/About)
Authors will need to create an account on the platform (if they do not already have one) at: https://cmt3.research.microsoft.com/docs/help/general/account-creation.html
Each abstract should be a maximum of 1 page.
Notification of accepted abstracts will be communicated on 22 Jun 2026.
MLESM Hackathon
The workshop follows the Hackathon on Machine Learning for the Earth System on 19-21 August 2026 in Bonn. Please find more information on how to apply here:
Local Organising Committee
Workshop Programme 24 – 26 Aug 2026
All times are in CEST (UTC+2)
For the abstracts, please click the respective title.
Monday 24 Aug:
08:30 – 09:00 Registration
9:00-10:30 NWP
- Welcoming Remarks
- Sophie Buurman & Aram Farhad Salihi: Multi-domain dynamical graph training of Bris for high-resolution on-demand forecasts (Long talk)
- Joel Oskarsson & Simon Adamov: Building Machine Learning Limited Area Models: Kilometer-Scale Weather Forecasting in Realistic Settings (Long talk)
- Maurice Schmeits: Comparative Verification of Deterministic ML Weather Prediction Models: Limited Area Modeling vs. Stretched-Grid Approaches over Europe
- Mario Santa Cruz: The AIFS: ECMWF’s data-driven weather forecasting system
- Stéphane Beauregard: Canada’s Hybrid AI-Physics Global Deterministic Prediction System with Spectral Nudging: Evaluation and Path to Operationalisation
11:00 – 11:55 NWP + Evaluation poster session
- Lightning talks (15 mins)
- Poster viewing
11:55 – 12:30 Evaluation
- Francesco Pasquini: Assessing the ability of a stretched-grid deep learning weather prediction model to learn the physics of wind storms
- Rodrigo Almeida: Can AI weather models capture rare events? A case study of the 2022 Pakistan floods
- Massimo Bonavita: Verification of Machine Learning models using Information and Noise
12:30 – 13:30 Lunch Break
13:30 – 15:00 Earth system components
- Nina Raoult & Rachel Furner: Beyond the atmosphere: Building a Data-Driven Earth System Model at ECMWF (Long talk)
- Mohamad Hakam Shams Eddin: RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
- Julia Kaltenborn: Towards Snowpack Emulation
- Tobias Finn: Going with the flow: towards physically consistent data-driven sea-ice models
15:30 – 16:30 Earth system component posters
- Lightning talks (20 mins)
- Poster viewing
16:30 – 17:30: Evaluation + NWP
- Kate Musgrave: Evaluation of Tropical Cyclone Forecasts from Artificial Intelligence Weather Prediction (AIWP) Models
- Leonardo Olivetti: Whose Weather Is It? Building a Fairness Evaluation Framework for Global Data-Driven Weather Forecasting Models
- Hyesook Lee: Toward Trustworthy and Transparent Nowcasting: A Concept-Based Explanation Framework for NowAlpha
- Amy McGovern: Extreme Weather Bench: A framework for evaluating AI weather models on high-impact weather
19:00 – : Workshop Dinner @ Tuscolo Münsterblick (Gerhard-von-Are-Straße 8, 53111 Bonn)
————————————
Tuesday 25 Aug:
9:00 – 10:30 Observations
- Gideon Dresdner: AIDA: Operational AI Data Assimilation from Level 1 Observations (Long talk)
- Zekun Ni: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
- Haiyu Dong: OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations
- Randy Chase: ICgen: A method to generate initial conditions from Tomorrow.io’s constellation of microwave sounders using score based data assimilation
- Simon De Kock: RUSH: An AI-Native Framework Combining Radar, Satellite, and Global AI Forecasts for Rapid-Update Precipitation Prediction over Belgium
11:00 – 12:00 Observation + Evaluation posters
- Lightning talks (20 mins)
- Poster viewing
12:00 – 12:30 Datasets
- Roope Tervo: Supporting Weather and Climate Application Development with ML-Friendly Earth Observation Data
- John Haynes: CIRA satellite data products for potential use in AIWP model training and evaluation
- Annemarie Bäthge: GROW: A Global Time Series Dataset for Groundwater Studies within the Earth System
12:30 – 13:30 Lunch Break
13:30 – 15:00 Foundation Models and NWP
- Christian Lessig: The WeatherGenerator: a foundation model for weather and climate
- Firat Ozdemir: Earth System Foundation Model (ESFM) – Extending Aurora to heterogeneous datasets
- Fanny Lehmann: Integrating the Water Cycle in the Earth System Foundation Model: one Path towards Subseasonal-to-Seasonal Predictions
- Michael Langguth: RAINA Nowcasting – High-resolution nowcasting of precipitation and wind extremes with a foundation model for the atmosphere
- Daniel Abdi: Development of data-driven emulator for the High-Resolution Rapid Refresh (HRRR) model (Long talk)
15:30 – 16:30 Evaluation + Climate Posters
- Lightning talks (20 mins)
- Poster viewing
16:30 – 17:30: NWP + Observations
- Zheng Wu: Assessing predictions of stratosphere-troposphere coupling of GraphCast
- Amaury Lancelin: Coupling AI Emulators and Rare Event Algorithms to Sample Extreme Heatwaves
- Thomas Hamill: Prototyping short-range, deep-learning-based probabilistic forecasts of precipitation: a collaboration between The Weather Company and NVIDIA
- Stephen Penny: Integrating machine learning with data assimilation to incorporate Earth system observations into MLWP forecasts
————————————
Wednesday 26 Aug:
9:00 – 10:30 Climate
- Nathaniel Cresswell-Clay: A Deep Learning Coupled Atmosphere-Ocean-Land Model for Weather and Climate Simulation (Long talk)
- Robert Brunstein: From Weather to Climate: Assessing Stability, Structure, and Skill of Arches Weather under Long Rollouts
- Graham Clyne: Interpolating in Climate Model Scenario Space using Generative Machine Learning
- Amaury Lancelin: Beyond the Unseen: Assessing AI Climate Emulators’ Capacity to Simulate Very Rare Events
- Elena Tomasi: Deep learning for high-resolution climate projections: a Latent Diffusion Model emulating dynamical downscaling of precipitation and temperature
11:00 – 12:00 Observation + Earth system components
- Emanuele Mele: Generative AI for Data Assimilation in the Ocean
- Italo Epicoco: MedFormer: a data-driven model for ocean forecast (Long talk)
- Jakob Schloer: A data-driven model for sub-seasonal forecasts
- Steffen Tietsche: Data-driven sub-seasonal forecasts with a stratosphere
- Vitus Benson: Neural networks in atmospheric transport and inverse modeling
12:00 – 12:15 Closing remarks
————————————-
Important Note: Long talk = 20 min , Regular talk = 10 min
List of Posters
Posters sessions:
S1: Monday 24 Aug. 11:00 – 11:55 S2: Monday 24 Aug. 15:30 – 16:30
S3: Tuesday 25 Aug. 11:00 – 12:00 S4: Tuesday 25 Aug. 15:30 – 16:30
Questions?
📩 Contact us at: mlesm-workshop@cesoc.net
Accommodation
Bonn offers a variety of hotels at different price points. We recommend booking early, as hotels can fill up quickly. Suggestions:
🏨 Motel One Bonn
🏨 IntercityHotel Bonn
🏨 Hotel Kurfürstenhof
Important Information
Information about the workshop for all registered participants will be sent via mlesm-workshop@cesoc.net or mlesm-registrations@cesoc.net. Please make sure to mark them as safe, i.e., not spam/junk.No time to attend our MLESM event but interested anyway, stay tuned and subscribe at mlesm-workshop@listen.uni-bonn.de.
For questions please contact us via email: mlesm-workshop@cesoc.net
MLESM Hackathon
The workshop follows the Hackathon on Machine Learning for the Earth System on 19-21 August 2026 in Bonn. Please find more information on how to apply here:
Supported by
We gratefully acknowledge the support by CESOC, ECMWF, the TRA Modelling at the University of Bonn, the Forschungszentrum Jülich and the University of Cologne.
Acknowledgement: The Microsoft CMT service will be used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.