Kraków, Poland, 16-18 June 2021 17-18 June 2021 on Zoom as a virtual event - please find the program at the end of this page!

ICCS 2021 : https://www.iccs-meeting.org/iccs2021/thematic-tracks/

... previous editions, MLDADS2020 , MLDADS 2019

Title: Machine Learning and Data Assimilation for Dynamical Systems - MLDADS 2021

Organisers: Dr. Rossella Arcucci, Diana O'Malley and Prof. Yi-Ke Guo

Dr. Cesar Quilodran Casas, Dr. Sibo Cheng, Jake Lever and Philip Nadler.

Important Dates:

• Paper submission: 12 February 2021 (extended)

• Notification to authors: 15 March 2021

• Camera-ready papers: 5 April 2021

• Author registration: 29 January – 5 March 2021

• Non-author early registration: 29 January – 23 April 2021

• Non-author late registration: from 24 April 2021

• ICCS Conference sessions: 16-18 June 2021 - MLDADS sessions: 17-18 June 2021

Abstract: The object of the theory of dynamical systems addresses the qualitative behaviour of dynamical systems as understood from models. Moreover, models are often not perfect and can be improved using data using tools from the field of Data Assimilation. Additionally, the field of Machine Learning is concerned with algorithms designed to accomplish certain tasks whose performance improve with the input of more data. The intersection of the fields of dynamical systems, data assimilation and machine learning is largely unexplored. The goal of this workshop is to bring together researchers from these fields to fill the gap between these theories.

Call for Papers: The intersection of the fields data assimilation, machine learning and dynamical systems is largely unexplored, and the goal of the MLDADS workshop is to bring together contributions from these fields to fill the gap between these theories in the following directions:

1) Machine Learning for Data Assimilation: how to assist or replace the traditional methods in making forecasts, without the unrealistic assumption (particularly linearity, normality and zero error covariance) of the conventional methods.

2) Machine Learning for Dynamical Systems: how to analyze dynamical systems on the basis of observed data rather than attempt to study them analytically.

3) Data Assimilation for Machine Learning and/or Dynamical Systems: how well does the model under consideration (Machine Learning model and/or Dynamical System) represent the physical phenomena.

4) Data Assimilation and Machine Learning for Dynamical Systems: how can tools from the interaction between the theories of Data Assimilation and Machine Learning be used to improve the accuracy of the prediction of dynamical systems.

Program Committee:

• Celine Robardet, National Institute of Applied Science in Lyon, France.

• Roland Potthast, Deutscher Wetterdienst (DWD), Germany.

• Ionel Michael Navon, Florida State University, Florida US.

• Marta Chinnici, National Agency for New Technologies, Energy and Sustainable Economic Development, Italy.

• Andrew M. Moore, University of California Santa Cruz, California US.

• Nancy Nichols, University of Reading, UK.

• Livia, Marcellino, University of Naples Parthenope, Italy.

• Tiziana Di Matteo, Kings College, UK.

• Gianluca, Bontempi, Université Libre de Bruxelles, Belgium.

• Massimiliano Pontil, UCL and Istituto Italiano di Tecnologia, UK and Italy.

• Luca Magri, Cambridge University, UK.

• Marco Gallieri, NNAISENSE, Switzerland.

• Vishwas Hebbur Venkata Subba Rao, Argonne National Laboratory, Lemont, IL.

• Gabriele Santin, Fondazione Bruno Kessler, Italy.

• Alberto Carrassi, University of Reading, UK.

Procedures for Submission:

1) Visit EasyChair Home, if you do not have an account in EasyChair.

2) Prepare the manuscripts (Abstract up to 2 pages, Short Paper up to 7 pages and Full Paper up to 14 pages), written in English and formatted according to the Springer LNCS templates. Templates are available for download in EasyChair horizontal menu "Templates" in the ICCS 2021 submission site in EasyChair.

During submission, you may select either a “Full/Short Paper” or a “Abstract Only” publication. By default, it would be an oral presentation. If you prefer to present a poster, please check the “Poster Presentation” option in the submission page..

3) Submit your paper to the ICCS 2021 submission site in EasyChair https://easychair.org/conferences/?conf=iccs2021

Choose the following track when being prompted for "Select a Track": Machine Learning and Data Assimilation for Dynamical Systems

For information please contact Dr. Rossella Arcucci, r.arcucci@imperial.ac.uk

Program (all times are CEST):

Thursday, June 17th

16:10-17:50 Session 11E: MLDADS 1 - (chair Rossella Arcucci)

16:10

Dennis Knol, Fons de Leeuw, Jan Fokke Meirink and Valeria Krzhizhanovskaya

Deep Learning for Solar Irradiance Nowcasting: A Comparison of a Recurrent Neural Network and Two Traditional Methods (abstract)

16:30

Alberto Racca and Luca Magri

Automatic-differentiated Physics-Informed Echo State Network (API-ESN) (abstract)

16:50

Marcella Torres

A machine learning method for parameter estimation and sensitivity analysis (abstract)

17:10

Nguyen Anh Khoa Doan, Wolfgang Polifke and Luca Magri

Auto-Encoded Reservoir Computing for Turbulence Learning (abstract)

17:30

Muzammil Hussain Rammay, Sergey Alyaev, Ahmed H. Elsheikh and Reidar Brumer Bratvold

Real-time probabilistic inversion of DNN-based DeepEM model while accounting for model error (abstract)

Friday, June 18^th

10:20-12:00 Session 13G: MLDADS 2 - (chair Sibo Cheng)

10:20

Alban Farchi, Patrick Laloyaux, Massimo Bonavita and Marc Bocquet

Using machine learning to correct model error in data assimilation and forecast applications (abstract)

10:40

Blas Kolic, Juan Sabuco and J. Doyne Farmer

From macro to micro and back: Microstates initialization from chaotic aggregate time series (abstract)

11:00

Maciej Filiński, Paweł Wachel and Koen Tiels

Low-dimensional Decompositions for Nonlinear Finite Impulse Response Modeling (abstract)

11:20

Jamal Afzali, Cesar Quilodran Casas and Rossella Arcucci

Latent GAN: using a latent space-based GAN for rapid forecasting of CFD models (abstract)

11:40

Maria Reinhardt, Sybille Schoger, Frederik Kurzrock, Roland Potthast and Louis-Etienne Boudreault

Intelligent Camera Cloud Operators for Convective Scale Numerical Weather Prediction (abstract)

14:00-15:40 Session 15G: MLDADS 3 - (chair Sibo Cheng and Cesar Quilodran Casas)

14:00

Maddalena Amendola, Rossella Arcucci, Laetitia Mottet, Cesar Quilodran Casas, Shiwei Fan, Christopher Pain, Paul Linden and Yi-Ke Guo

Data Assimilation in the Latent Space of a Convolutional Autoencoder (abstract)

14:20

Giuseppe Brandi and Tiziana Di Matteo

Higher-order hierarchical spectral clustering for multidimensional data (abstract)

14:40

Zainab Titus, Claire Heaney, Carl Jacquemyn, Pablo Salinas, Matthew Jackson and Christopher Pain

Neural Networks for Conditioning Surface-Based Geological Models with Uncertainty Analysis (abstract)

15:00

Juan Gomez Romero and Miguel Molina-Solana

Towards data-driven simulation models for building energy management (abstract)

15:20

Maximilian Croci, Ushnish Sengupta and Matthew Juniper

Data Assimilation using Heteroscedastic Bayesian Neural Network Ensembles for Reduced-Order Flame Models (abstract)

16:10-17:10 Session 16G: MLDADS 4 - (chair Cesar Quilodran Casas)

16:10

Stefano Fiscale, Pasquale De Luca, Laura Inno, Livia Marcellino, Ardelio Galletti, Alessandra Rotundi, Angelo Ciaramella, Giovanni Covone and Elisa Quintana

A GPU algorithm for Outliers detection in TESS light curves (abstract)

16:30

Varuni Katti Sastry, Romit Maulik, Vishwas Hebbur Venkata Subba Rao, Sudarshan Ashwin Renganathan and Rao Kotamarthi

Data-driven deep learning emulators for geophysical forecasting (abstract)

16:50

Oliver Hennigh, Susheela Narasimhan, Mohammad Amin Nabian, Akshay Subramaniam, Kaustubh Tangsali, Max Rietmann, Jose del Aguila Ferrandis, Wonmin Byeon, Zhiwei Fang and Sanjay Choudhry

NVIDIA SimNet™: An AI-Accelerated Multi-Physics Simulation Framework (abstract)