MAELSTROM dissemination workshop (28 March) and Machine Learning Workshop (29 March - 1 April)

Name: MAELSTROM dissemination workshop (28 March) and Machine Learning Workshop (29 March - 1 April)
Start: 2022-03-28T08:30:00+01:00
End: 2022-04-01T17:40:00+01:00
Location: Virtual

Monday, 28 March
	MAELSTROM Workshop: Updates on MAELSTROM
08:30 → 08:50	Introduction Speaker: Peter Dueben (ECMWF) Presentation Recording	Virtual	20m
08:50 → 09:10	WP1 Summary on Applications and Data Sets Speaker: Bing Gong (JSC) Presentation Recording	Virtual	20m
09:10 → 09:30	WP2 Summary on Software Tools Speaker: Fabian Emmerich (4-cast) Presentation Recording	Virtual	20m
09:30 → 09:50	WP3 Summary on Hardware Benchmarks Speakers: Andreas Herten (JSC), Daniele Gregori (E4 Computer Engineering SPA) Presentation Recording	Virtual	20m
09:50 → 10:30	Possibility for general discussion Recording	Virtual	40m
10:30 → 11:00	Coffee break	Virtual	30m
	EuroHPC Partner Project Talks
11:00 → 11:20	TimeX Speakers: Giovanni Samaey (KU Leuven), Martin Schreiber (Technical University of Munich) Presentation Recording	Virtual	20m
11:20 → 11:40	Deep-Sea Speaker: Estela Suarez (JSC) Presentation Recording	Virtual	20m
11:40 → 12:00	Red-Sea Speaker: Nikos Xrysos (FORTH) Recording	Virtual	20m
12:00 → 12:30	Discussions between MAELSTROM and the speakers Recording	Virtual	30m
12:30 → 13:30	Lunch break	Virtual	1h
	External Science Talks
13:30 → 14:00	Time-Consistent Downscaling of Atmospheric Fields with Generative Adversarial Networks Speaker: Jussi Leinonen (MeteoSwiss) Presentation Recording	Virtual	30m
14:00 → 14:30	Pangeo: An Open Source Ecosystem for Data-Intensive Science Speaker: Ryan Abernathey (Columbia University) Presentation Recording	Virtual	30m
14:30 → 15:00	Deep Learning for Earth Sciences in the HPC Context Speaker: Thorsten Kurth (NVIDIA Corporation) Presentation Recording	Virtual	30m
15:00 → 15:30	Discussions between MAELSTROM and the speakers Recording	Virtual	30m
15:30 → 16:00	Coffee break	Virtual	30m
16:00 → 17:30	Possibility for further discussions between the working groups	Virtual	1h 30m
Tuesday, 29 March
	Machine Learning Workshop: Session 1: Machine learning for emulation of model components Chair: Matthew Chantry (ECMWF)
09:40 → 10:00	Welcome and introduction Speakers: Florian Pappenberger (ECMWF), Peter Dueben (ECMWF) Recording	Virtual	20m
10:00 → 10:20	Climate-Invariant, Causally Consistent Neural Networks as Robust Emulators of Subgrid Processes across Climates Speaker: Tom Beucler (University of Lausanne) Presentation Recording	Virtual	20m
10:20 → 10:40	How AI/ML interpenetrate into Weather Forecast: NN emulator for radiation parameterization and Retrieval similar weather condition using satellite images Speaker: Hyesook Lee (Director of AI Weather Forecast Research Division) Recording	Virtual	20m
10:40 → 11:00	ClimateBench: A benchmark dataset for data-driven climate projections Speaker: Duncan Watson-Parris (University of Oxford) Presentation Recording	Virtual	20m
11:00 → 11:20	Why and how to learn end-to-end subgrid closures for atmosphere and ocean models? Speaker: Julien Le Sommer (IGE, UGA/CNRS/IRD/G-INP) Presentation Recording	Virtual	20m
11:20 → 11:40	Coffee break	Virtual	20m
11:40 → 12:40	Poster session	Virtual	1h
12:40 → 14:00	Lunch break	Virtual	1h 20m
14:00 → 14:20	Developing an emulator of an Ocean GCM Speaker: Rachel Furner (University of Cambridge) Presentation Recording	Virtual	20m
14:20 → 14:40	An Online-Learned Neural Network Chemical Solver for Stable Long-Term Global Simulations of Atmospheric Chemistry Speaker: Makoto Kelp (Harvard University) Presentation Recording	Virtual	20m
14:40 → 15:00	Neural-network parameterization of subgrid momentum transport learned from a high-resolution simulation Speaker: Janni Yuval (MIT) Presentation Recording	Virtual	20m
15:00 → 15:40	Coffee break	Virtual	40m
15:40 → 16:00	Machine learning for gravity waves in a climate model Speaker: Steven Hardiman (Met Office) Presentation Recording	Virtual	20m
16:00 → 16:20	Physics-Informed Learning of Aerosol Microphysics Speaker: Paula Harder (Fraunhofer Institute ITWM) Presentation Recording	Virtual	20m
16:20 → 16:40	Neural network emulation of precipitation and condensation processes in FV3GFS Speaker: Noah Brenowitz (Allen AI) Presentation Recording	Virtual	20m
16:40 → 17:00	Towards physics-based machine learning for land surface modeling: The case of land-atmosphere interactions Speaker: Andrew Bennett (University of Washington) Presentation Recording	Virtual	20m
17:00 → 17:15	Coffee break	Virtual	15m
17:15 → 18:00	Discussion with all speakers - moderated by Matthew Chantry	Virtual	45m
Wednesday, 30 March
	Session 2: Machine learning for forecasts from now-casting to seasonal Chair: Peter Dueben (ECMWF)
09:30 → 09:50	High-Resolution Solar Power Nowcasting by Deep Learning: How to Extract Features from Historic Time Series, Remote Sensing, and Numeric Weather Prediction Models to achieve Optimized Machine Learning Forecasts Speaker: Petrina Papazek (ZAMG) Presentation Recording	Virtual	20m
09:50 → 10:10	Improving sub-seasonal forecasts by correcting missing teleconnections using ANN-based post-processing Speaker: Chiem van Straaten (KNMI) Presentation Recording	Virtual	20m
10:10 → 10:30	Interpretable Deep Learning for Probabilistic MJO Prediction Speaker: Antoine Delaunay (Ecole Polytechnique / Imperial College London ) Presentation Recording	Virtual	20m
10:30 → 10:50	Convolutional neural networks for skillful global probabilistic prediction of temperature and precipitation on sub-seasonal time-scales Speaker: Nina Horat (Karlsruhe Institute of Technology, Department of Economics, Institute of Econometrics and Statistics) Presentation Recording	Virtual	20m
11:00 → 11:30	Break	Virtual	30m
	Session 2a: Machine learning for forecasts from now-casting to seasonal Chair: Shraddha Gupta (ECMWF)
11:30 → 11:50	Identifying relevant large-scale predictors for sub-seasonal precipitation forecast using explainable neural networks Speaker: Niclas Rieger (Centre de Recerca Matemática (CRM)) Presentation Recording	Virtual	20m
11:50 → 12:10	Ensemble forecast of the Madden Julian Oscillation using a stochastic weather generator based on analogs of Z500 Speaker: Meriem Krouma (ARIA Technologies; Laboratoire des Sciences du Climat et de l’Environnement, UMR 8212 CEA-CNRS-UVSQ, IPSL \& Université Paris-Saclay) Presentation Recording	Virtual	20m
12:10 → 12:30	Improving the prediction of the Madden-Julian Oscillation of the ECMWF model by post-processing Speaker: Riccardo Silini (Universitat politecnica de Catalunya) Presentation Recording	Virtual	20m
12:30 → 12:50	Sub-Seasonal Probabilistic Precipitation Forecasting using Extreme Learning Machine Speakers: Kyle Hall (International Research Institute for Climate & Society), Nachiketa Acharya (Pennsylvania State University) Recording	Virtual	20m
13:00 → 15:00	Lunch break	Virtual	2h
	Session 2b: Machine learning for forecasts from now-casting to seasonal Chair: Nikolaos Mastrantonas (ECMWF)
15:00 → 15:20	Opportunistic mixture model for post-processing S2S temperature and precipitation forecasts using convolutional neural networks Speaker: David Landry (Computer Research Institute of Montreal) Presentation Recording	Virtual	20m
15:20 → 15:40	Deep learning augmented numerical weather prediction digital twin experiments for global precipitation forecasting Speaker: Manmeet Singh (University of Texas) Presentation Recording	Virtual	20m
15:40 → 16:00	Improving medium-range ensemble forecasts with transformers Speaker: Jonathan Weyn (Microsoft) Presentation Recording	Virtual	20m
16:00 → 16:20	Forecasting Global Weather with Graph Neural Networks Speaker: Ryan Keisler ML-WS_Keisler.pdf Recording	Virtual	20m
16:20 → 16:40	Deep learning weather prediction: epistemology and new scientific horizons Speaker: Dale Durran (University of Washington, Seattle) Presentation Recording	Virtual	20m
16:40 → 17:00	Coffee break	Virtual	20m
17:00 → 17:45	Discussion with all speakers - moderated by Peter Dueben Recording	Virtual	45m
Thursday, 31 March
	Session 3: Machine learning for feature detection and user applications Chair: Mihai Alexe (ECMWF)
10:00 → 10:20	A Machine Learning Approach to Stochastic Downscaling of Precipitation Forecasts Speaker: Lucy Harris (AOPP at Oxford University) Presentation Recording	Virtual	20m
10:20 → 10:40	Causal deep learning for studying the Earth system: soil moisture-precipitation coupling in ERA5 data across Europe Speaker: Tobias Tesch (Forschungszentrum Jülich) Presentation Recording	Virtual	20m
10:40 → 11:00	Rainfall scenarios from AROME-EPS forecasts using autoencoder and climatological patterns Speaker: Arnaud Mounier (Météo-France) Presentation Recording	Virtual	20m
11:00 → 11:20	Utilizing self-learning capability of a deep neural network and continuous monitoring of geostationary satellite to understand clouds structure and organization. Speaker: Dwaipayan Chatterjee (Institute for Geophysics and Meteorology,University of Cologne) Presentation Recording	Virtual	20m
11:30 → 13:00	Lunch break	Virtual	1h 30m
	Session 3a: Machine learning for feature detection and user applications Chair: Jesper Dramsch (ECMWF)
13:00 → 13:20	ML-based fire hazard model trained on thermal infrared satellite data Speaker: Julia Gottfriedsen (Ludwig Maximilian University of Munich (LMU), OroraTech) Presentation Recording	Virtual	20m
13:20 → 13:40	Photographic Visualization of Weather Forecasts with Generative Adversarial Networks Speaker: Christian Sigg (MeteoSwiss) Presentation Recording	Virtual	20m
13:40 → 14:00	Identifying Lightning Processes in ERA5 Soundings with Deep Learning Speaker: Gregor Ehrensperger (Department of Mathematics, University of Innsbruck) Presentation Recording	Virtual	20m
14:00 → 14:20	Deep Learning for the Verification of Synoptic-scale Processes in NWP and Climate Models Speaker: Julian Quinting (Karlsruhe Institute of Technology) Presentation Recording	Virtual	20m
14:30 → 15:00	Coffee break	Virtual	30m
	Session 3b: Machine learning for feature detection and user applications Chair: Mihai Alexe (ECMWF)
15:00 → 15:20	Latent space, feature space and the global domain – how ozone research can benefit from explainable machine learning Speaker: Clara Betancourt (Jülich Supercomputing Centre) Presentation Recording	Virtual	20m
15:20 → 15:40	Learning from Noisy Class Labels for Earth Observation Speaker: Begüm Demir (TU Berlin) Presentation Recording	Virtual	20m
15:40 → 16:00	Generative Adversarial Networks for Extreme Super-Resolution and Downscaling of Wind Fields at Convection-Permitting Scales Speaker: Nic Annau (Environment and Climate Change Canada, University of Victoria) Presentation Recording	Virtual	20m
16:00 → 16:20	A machine learning correction model for the warm bias over Arctic sea ice in atmospheric reanalyses Speaker: Lorenzo Zampieri (National Center for Atmospheric Research (NCAR)) Presentation Recording	Virtual	20m
16:30 → 16:45	Coffee break	Virtual	15m
16:45 → 17:30	Discussion with all speakers - moderated by Mihai Alexe Recording	Virtual	45m
Friday, 1 April
	Session 3c: Machine learning for feature detection and user applications Chair: Mihai Alexe (ECMWF)
09:00 → 09:20	Spatially coherent postprocessing of cloud cover and precipitation forecasts using generative adversarial networks Speaker: Stephan Hemri (University of Zurich) Presentation Recording	Virtual	20m
09:20 → 09:40	Improvements of the Adriatic Deep-Learning Sea Level Modeling Network HIDRA Speaker: Marko Rus (Faculty of Computer and Information Science, Visual Cognitive Systems Lab, University of Ljubljana) Presentation Recording	Virtual	20m
09:40 → 10:00	Spatio-temporal Forecasting of Meteorological Visibility over Northwest of Morocco using Long short-term memory (LSTM) network. Speaker: Badreddine Alaoui ((1) Hassania School of Public Works, LaGeS/ MoNum ; (2) Direction Générale de la Météorologie, CNRM) Presentation Recording	Virtual	20m
10:00 → 10:30	Break	Virtual	30m
	Session 4: Machine learning tools and high-performance computing Chair: Peter Dueben (ECMWF)
10:30 → 10:50	The European Destination Earth project and its potential for boosting machine learning Speaker: Peter Bauer (ECMWF) Presentation Recording	Virtual	20m
10:50 → 11:10	Convergence of HPC and Data Science at the Edinburgh International Data Facility Speaker: Mark Parsons (EPCC, The University of Edinburgh) Presentation Recording	Virtual	20m
11:10 → 11:30	Improving the radiative scheme with machine learning on an heterogeneous cluster Speakers: Rémi Druilhe (Atos), Christophe Bovalo (Atos) Presentation Recording	Virtual	20m
11:30 → 11:50	Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling Speaker: Niv Giladi (Technion - Israel Institute of Technology) Recording	Virtual	20m
12:00 → 13:00	Lunch break	Virtual	1h
13:00 → 13:20	Improving rare events predictions by oversampling tabular data with a mix of categorical and continuous variables by generative adversarial networks Speaker: Alla Sapronova (StormGeo) Presentation Recording	Virtual	20m
	Session 4a: Machine learning tools and high-performance computing Chair: Florian Pinault (ECMWF)
13:20 → 13:40	Generative machine learning for extreme climate scenarios Speaker: Bianca Zadrozny (IBM Research) Presentation Recording	Virtual	20m
13:40 → 14:00	Use of Machine learning for the detection and classification of observation anomalies Speaker: Mohamed Dahoui (ECMWF) Presentation Recording	Virtual	20m
14:00 → 14:20	Building Digital Twins of the Earth for NVIDIA’s Earth-2 Initiative Speakers: Karthik Kashinath (NVIDIA Corporation), Jaideep Pathak (NVIDIA) Presentation Recording	Virtual	20m
14:30 → 15:00	Coffee break	Virtual	30m
15:00 → 15:20	Exploring the Use of Machine Learning and Remote Sensing for Traffic Map Generation at Large Scale Speaker: Taha Alfaqheri (4EI) Presentation.pdf	Virtual	20m
15:20 → 15:40	Tropical Extreme Weather Event Management and Climate Adaptation via Supervised Computer Vision-based Algorithms Speaker: Thomas Chen (Academy for Mathematics, Science, and Engineering) Presentation Recording	Virtual	20m
15:40 → 16:00	Accelerating computational fluid dynamics with deep learning Speaker: Stephan Hoyer (Google Research) ML-WS_Hoyer.pdf Recording	Virtual	20m
16:00 → 16:15	Coffee break	Virtual	15m
16:15 → 17:00	Discussion with all speakers - moderated by Florian Pinault Recording	Virtual	45m

Please select a timezone to show adjusted event times accordingly.