Virtual Event: ECMWF-ESA Workshop on Machine Learning for Earth System Observation and Prediction

Name: Virtual Event: ECMWF-ESA Workshop on Machine Learning for Earth System Observation and Prediction
Start: 2020-10-05T11:00:00+01:00
End: 2020-10-08T15:30:00+01:00
Location: ECMWF

Overview
Presentations and recordings
Posters
Thematic areas
Call for Abstracts

Reviewing Area

Organising Committee
Contact

Material Package

Added Since

Navigate forward to interact with the calendar and select a date. Press the question mark key to get the keyboard shortcuts for changing dates.

Include only attachments uploaded after this date

Include*

Everything

Specific sessions

Specific contributions

Specific days

Sessions*

Session 1: ML for the Earth System - Setting the scene

Session 2: ML for Earth System Observations

Session 2 (cont.): ML for Earth System Observations

Session 3: ML for Data Assimilation

Session 3 (cont.) and Session 4: ML for Data Assimilation and ML for Product Development

Session 4 (cont.): ML for Product Development

Session 4 (cont.) and Session 5: ML for Product Development and ML for Model Identification and development

Session 5 (cont.): ML for Model Identification and development

Poster session

Session 3 (cont.): ML for Data Assimilation

Working groups

WG chairs finalise reports

Working Groups plenary discussion and close

Include materials from selected sessions

Contributions*

Accelerating and Explaining Earth System Process Models with Machine Learning (in session "Session 1: ML for the Earth System - Setting the scene")

Analog Forecasting of Extreme‐Causing Weather Patterns Using Deep Learning (in session "Session 5 (cont.): ML for Model Identification and development")

Artificial Intelligence in ESA Contribution to the United Nations Framework Convention on Climate Change (UNFCCC) : An Overview (in session "Session 2 (cont.): ML for Earth System Observations")

Artificial Neural Network at the service of Data Assimilation (and vice versa) (in session "Session 3: ML for Data Assimilation")

Assessing Machine Learning Approaches for Physical Parameterizations in Atmospheric General Circulation Models (in session "Session 5 (cont.): ML for Model Identification and development")

Automatic detection of weather events in high-resolution NWP outputs (in session "Session 4 (cont.): ML for Product Development")

Bayesian Deep Learning for Data Assimilation (in session "Session 3 (cont.) and Session 4: ML for Data Assimilation and ML for Product Development")

Big Data, Big Computation, and Machine Learning in Numerical Weather Prediction (in session "Session 3: ML for Data Assimilation")

Combining data assimilation and machine learning to emulate hidden dynamics and to infer unresolved scale pametrisation. (in session "Session 3: ML for Data Assimilation")

Data Assimilation and Machine Learning Science at ECMWF (in session "Session 3 (cont.): ML for Data Assimilation")

Deep Hashing for Scalable Remote Sensing Image Retrieval in Large Archives (in session "Session 2 (cont.): ML for Earth System Observations")

Deep Learning for Post-Processing Ensemble Weather Forecasts (in session "Session 3 (cont.) and Session 4: ML for Data Assimilation and ML for Product Development")

Deep Unsupervised Learning for Climate Informatics (in session "Session 3 (cont.) and Session 4: ML for Data Assimilation and ML for Product Development")

Description of Working Groups (in session "Session 5 (cont.): ML for Model Identification and development")

Emulation of gravity wave parameterisation in weather forecasting (in session "Session 4 (cont.) and Session 5: ML for Product Development and ML for Model Identification and development")

Exploring the Frontiers of Deep Learning for Earth System Observation and Prediction (in session "Session 2: ML for Earth System Observations")

Hyperparameter learning in data assimilation systems (in session "Session 3 (cont.): ML for Data Assimilation")

Joint learning of variational data assimilation models and solvers (in session "Session 3 (cont.): ML for Data Assimilation")

Learning from earth system observations: machine learning or data assimilation? (in session "Session 1: ML for the Earth System - Setting the scene")

Leveraging Modern AI/ML Techniques in NWP Including Data Fusion/Assimilation (in session "Session 2: ML for Earth System Observations")

Machine learning at ECMWF (in session "Session 4 (cont.): ML for Product Development")

Machine Learning for Applied Weather Prediction (in session "Session 3 (cont.) and Session 4: ML for Data Assimilation and ML for Product Development")

Model optimization with a genetic algorithm (in session "Session 5 (cont.): ML for Model Identification and development")

Neural network products in land surface data assimilation (in session "Session 2 (cont.): ML for Earth System Observations")

Neural Networks for Postprocessing Ensemble Weather Forecasts (in session "Session 4 (cont.) and Session 5: ML for Product Development and ML for Model Identification and development")

On the Interpretation of Neural Networks Trained for Meteorological Applications (in session "Session 2 (cont.): ML for Earth System Observations")

Physics Guided Machine Learning: A New Framework for Accelerating Scientific Discovery (in session "Session 5 (cont.): ML for Model Identification and development")

Probabilistic Deep Learning for Postprocessing Wind Forecasts in Complex Terrain (in session "Session 4 (cont.): ML for Product Development")

S2S forecasting using large ensembles of data-driven global weather prediction models (in session "Session 5 (cont.): ML for Model Identification and development")

Significance-tested and physically constrained interpretation of a deep-learning model for tornadoes (in session "Session 4 (cont.) and Session 5: ML for Product Development and ML for Model Identification and development")

The Rise of AI for EO (in session "Session 2: ML for Earth System Observations")

Towards an end-to-end data-driven weather model (in session "Session 4 (cont.) and Session 5: ML for Product Development and ML for Model Identification and development")

Using machine learning and data assimilation to learn both dynamics and state (in session "Session 3: ML for Data Assimilation")

Using Machine Learning to advance hour-scale heavy rain forecast with high resolution ECMWF Global Model and Local Meso-scale Model Forecasts (in session "Session 2 (cont.): ML for Earth System Observations")

Welcome and introduction - ECMWF

Welcome and introduction - ESA

WG1 (Observations) chaired by Alan Geer (ECMWF) and Bertrand Le Saux (ESA/ESRIN) (in session "Working groups")

WG2 (Data Assimilation) chaired by Alberto Carrassi (Univ. of Reading) and Rosella Arcucci (Imperial College) (in session "Working groups")

WG3 (Models) chaired by Massimo Bonavita (ECMWF) and Peter Dueben (ECMWF) (in session "Working groups")

WG4 (Ensembles, Product Generation) chaired by Laure Raynaud (Météo-France) and Nicolas Longepe (ESA) (in session "Working groups")

What If The Easiest Part of the Global Atmospheric System For Machines To Learn Is The Dynamics? (in session "Session 5 (cont.): ML for Model Identification and development")

Include materials from selected contributions

Events scheduled on*

05/10/2020

06/10/2020

07/10/2020

08/10/2020

Include materials from sessions/contributions scheduled on the selected dates