Explainability and Trust - Part 3: Explaining a model you cannot check-

hace 6 días

Explainability and Trust - Part 3: Explaining a model you cannot check

Jesper Dramsch, a Scientist for Machine Learning at the European Centre for Medium-Range Weather Forecasts. They explore the why and how of explaining models and where these explanations should or should not be trusted. This video is part...

hace 33 días

Introduction - What It Takes to Make ML Work in Production at Scale

Ana Prieto Nemesio, Machine Learning Engineering Team Lead at ECMWF, shares the different pathways of data-driven weather forecasting application and production. This video is part of ECMWF's course "Machine Learning for Earth Systems Modelling: Applications and Future Directions", part...

hace 6 días

Explainability and Trust - Part 5: Trust, and what to do about it

hace 15 días

AI Weather Quest: Annual Highlights and Awards webinar

The AI Weather Quest: Annual Highlights and Awards webinar took place on 24 September 2026 as part of the WMO AI Webinar series. It highlighted achievements from the first year of the AI Weather Quest, shared scientific insights...

hace 33 días

Rainfall Runoff Simulation using LSTMs

Eduardo Acuña Espinoza, Researcher at the Institute of Water and Environment at KIT, explains how Long Short-Term Memory (LSTM) networks can be used to simulate rainfall–runoff processes and support hydrological prediction. This video is part of ECMWF's course "Machine...

hace 33 días

Machine Learning for Wildfire Danger Prediction

Carolina Natel de Moura, Postdoctoral Researcher at the Institute of Meteorology and Climate Research - Atmospheric Environmental Research at KIT, explains the application of machine learning for wildfire danger prediction. This video is part of ECMWF's course "Machine Learning...

hace 6 días

Explainability and Trust - Part 1: Introduction

hace 33 días

Machine Learning Diffusion Downscaling with Anemoi

Joffrey Dumont, Machine Learning and Uncertainty Quantification Scientist at ECMWF, explains why downscaling is needed and how machine learning can be used to generate high-resolution forecasts from lower-resolution predictions. He introduces diffusion-based downscaling and demonstrates how diffusion models...

hace 33 días

Foundation Models for the Earth System

Richard Turner, Professor of Machine Learning at the University of Cambridge, introduces foundation models for Earth systems modelling and explains their role in weather forecasting. Then he dives deeper into foundation model Aurora, how it works, which data...

hace 25 días

DestinE AI Earth System Sea Ice Component

As part of the various Artificial Intelligence (AI) and Machine Learning (ML) activities within DestinE, the development of new ML-based Earth system components plays a key role. This video introduces the development of the new ML-based sea...

hace 6 días

Explainability and Trust - Part 2: Explaining a model you can check

hace 6 días

Explainability and Trust - Part 4: Convincing but wrong

hace 33 días

Extreme Events and Extrapolation in Al Weather Models

Sebastian Engelke, Professor at the Research Institute for Statistics and Information Science at the University of Geneva, and Marco Frölich, PhD candidate at the University of Geneva, discuss the challenges of simulating extreme events and extrapolating in AI...

hace 21 días

Long-range forecasting

Katie Kowal, Director of AI for Weather at the University of Chicago Data Science Institute, explores how AI can be applied to sub-seasonal forecasting and how forecasting systems can move from research into real-world decision support. This video is...

hace 50 días

Climate Change Adaptation Digital Twin - system overview, simulations, evaluation and data access

The presentation provides an overview of the Climate Change Adaptation Digital Twin (Climate DT) of the European Commission's Destination Earth initiative. ECMWF Scientists Sebastian Milinski and Matthias Aengenheyster give an overview of the system, available simulations, evaluation and...