Annual workshops

Every year, the DataLearning group organises a workshop on Machine Learning and Data Assimilation for Dynamical Systems (MLDADS), as part of the International Conference on Computational Science (ICCS).

Read more about past editions of the MLDADS workshops below:
London - ICCS 2022
Poland - ICCS 2021
Amsterdam - ICCS 2020
Faro, Portugal - ICCS 2019


 

Weekly meetings

The DataLearning group has weekly meetings (Tuesdays, 4pm GMT), with invited speakers. The meetings are open to everyone - join the mailing list for more information.

See the upcoming event calendar here and view past topics below.

Weekly meeting tabs

2019
  • 19th March 2019: Kickoff Meeting

  • 26th March 2019: Neural Network technologies used for fake news detection - proposed by Julio C Amador Díaz López

  • 2nd April 2019: Fast data assimilation and forecasting the motion of the ocean - proposed by César A Quilodrán Casas

  • 9th April 2019: Integrating Semantic Knowledge to Tackle Zero-shot Text Classification - proposed by Jingqing Zhang

  • 16th April 2019: Adversarial Perturbations in the wild and their applications - proposed by Stefano Marrone

  • 7th May 2019: How to organise Deep Learning research - proposed by Mihai Suteu

  • 14th May 2019: What your network looks like? - proposed by James A Scott-Brown

  • 21st May 2019: Group discussion about the Kalman filter

  • 28th May 2019: 3D Variational DA and Neural Network - proposed by Robin Evers and Lamya Moutiq

  • 4th June 2019: Group discussion about Neural Ordinary Differential Equations

  • 11th June 2019: The DataLearning working group was in Faro (Portugal) for the first MLDADS 2019 workshop at ICCS

  • 18th June 2019: Group discussion about Machine Learning: Deepest Learning as Statistical Data Assimilation Problems

  • 25th June 2019: Optimizing Artificial Neural Networks by using Evolutionary Algorithms for Energy Consumption Forecasting - proposed by Luis Baca Ruiz

  • 2nd July 2019: Group discussion about Simulation-Based Optimization Frameworks for Urban Transportation Problems

  • 9th July 2019: Optimal sensors positioning using Gaussian Processes - proposed by Tolga Dur and Gabor Tajnafoi

  • 16th July 2019: Group discussion about Fixed rank kriging for very large spatial data sets

  • 23rd July 2019: A novel approach to monitor blood glucose using non-invasive body parameters - proposed by Shad A Asinger and Changavy Kajamuhan

  • 30th July 2019: Active network management in low-voltage networks using high-resolution substation data - proposed by Julio Perez Olvera

  • 17th September 2019: Group discussion about Bayesian Statistics in Machine Learning

  • 24th September 2019: Data assimilation technologies for parameter estimation - proposed by Philip Nadler

  • 1st October 2019: Convex Optimization for Parallel Energy Minimization - proposed by Sesh Kumar

  • 8th October 2019: Group discussion about Data assimilation as a deep learning tool to infer ODE representations of dynamical models

  • 15th October 2019: Effective Data Assimilation - proposed by Rossella Arcucci

  • 22nd October 2019: Inferring the unknown: Unifying statistical pre- and post-processing in meteorology with amortized variational inference - proposed by Tobias Finn

  • 29th October 2019: Group discussion about Generalisability of deep models

  • 5th November 2019: Group discussion about FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models

  • 12th November 2019: Group discussion about Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios

  • 19th November 2019: Graph Drawing by Stochastic Gradient Descent - proposed by Jonathan Zheng

  • 26th November 2019: Group discussion about tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow

  • 10th December 2019: Domain Decomposition Autoencoder - A neural network for compressing large datasets - proposed by Toby Phillips

2020
  • 14th January 2020: Data Assimilation using Second-Order Sensitivities - proposed by Zainab Titus

  • 21st January 2020: group discussion about Non-intrusive reduced order modeling of nonlinear problems using neural networks

  • 28th January 2020: group discussion about Deep Fluids: A Generative Network for Parameterized Fluid Simulations

  • 4th February 2020: Human in the loop: Design with Machine Learning - proposed by Pan Wang

  • 11th February 2020: group discussion about Low-dimensional recurrent neural network-based Kalman filter for speech enhancement

  • 18th February 2020: group discussion about End-to-end Optimized Image Compression with Attention Mechanism

  • 25th February 2020: group discussion about Deep Kalman Filters

  • 3rd March 2020: group discussion about SD-GAN: Structural and Denoising GAN

  • 10th March 2020: Can we use machine learning to predict global patterns of climate change? - proposed by Laura Mansfield

  • 17th March 2020 to 8th September 2020: The meetings have been cancelled because of Covid-19

  • 15th September 2020: Machine learning fluid dynamics modelling for urban air pollution - Latent GAN - proposed by Jamal Afzali

  • 22nd September 2020: Improving Econophysical Systems for blockchain and cryptocurrencies using Data Assimilation - by Pratha Khandelwal

  • 29th September 2020: Urban air pollution forecasts generated from latent space representation - by César Quilodrán

  • 6th October 2020: Increasing the visibility of low-voltage networks through data analytics - by Ronald Monterroso

  • 13th October 2020: Artificial Neural Network at the service of Data Assimilation (and vice versa) - by Rossella Arcucci

  • 20th October 2020: Correcting public opinion trends through machine learning and data assimilation - by Robin Hendrickx

  • 27th October 2020: Predicting the spatial variation of COVID-19 infections using generative adversarial networks - by Yaqi Li and Applying Convolutional Neural Networks to Data on Unstructured Meshes - by Yuling Li

  • 3rd November 2020: Unstructured Convolutional Autoencoders for Big Data Assimilation - by Maxime Redstone Leclerc

  • 10th November 2020: GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series - by Edward De Brouwer

  • 17th November 2020: How self-organizing maps can help us understand atmospheric blocking - by Carl Thomas

  • 24th November 2020: Error analysis of reduced-order modelling - by Dunhui Xiao (Swansea University)

  • 1st December 2020: Differentiable Physics Simulations for Deep Learning Algorithms - by Nils Thuerey (TUM) 

  • 15th December 2020: Predicting multidimensional data via tensor learning - by Giuseppe Brandi (King's College London)

2021
  • 5th January 2021: Machine learning for weather predictions - by Peter Dueben (ECMWF)

  • 19th January 2021: Accelerated Gaussian Convolution in a Data Assimilation scenario - by Pasquale De Luca (University of Salerno)

  • 26th January 2021: A Neural Implementation of the Kalman Filter - by Robert Wilson (University of Arizona)

  • 2nd February 2021: Graph-Based Generative Adversarial Networks for Data Generation in High Energy Physics - by Raghav Kansal (UC San Diego)

  • 9th February 2021: Turbulence Enrichment with Physics-informed Generative Adversarial Network - by Akshay Subramaniam (NVIDIA)

  • 16th February 2021: NVIDIA SimNet: an AI-accelerated multi-physics simulation framework - by Oliver Hennigh (NVIDIA)

  • 23th February 2021: Quantifying the presence of air pollutants over a road network in high spatio-temporal resolution - by Matteo Bohm (Sapienza University of Rome)

  • 2nd March 2021: Towards self-adaptive building energy control in smart grids - by Juan Gómez Romero (Universidad de Granada)

  • 9th March 2021: Towards practical global field reconstruction from sparse sensors with deep learning - by Kai Fukami (UCLA)

  • 16th March 2021: Utilization of autoencoder-based nonlinear manifolds for fluid flow forecasts driven with long short-term memory - by Taichi Nakamura (Keio University) 

  • 23rd March 2021: Deep Fire Topology: Understanding the role of landscape spatial patterns in wildfire susceptibility - by Cristóbal Pais Martínez (UC Berkeley) 

  • 30th March 2021: The World as a Graph: Improving El Niño Forecasts with Graph Neural Networks - by Salva Rühling Cachay (TU Darmstadt) 

  • 13th April 2021: Deep Learning Predictive Modelling in Combination with Data Assimilation and Applications to Geophysical Dynamics - by Fangxin Fang (ICL) 

  • 20th April 2021: Rare events and their optimization - by Vishwas Rao (Argonne National Laboratory)

  • 27th April 2021: MLDADS 2021 Webinar - Alberto Racca

  • 4th May 2021: A Tale of Three Implicit Planners and the XLVIN agent - by Petar Veličković (DeepMind)

  • 11th May 2021: Identify the dynamics of climate models using data assimilation and analog predictions - Pierre Tandeo (IMT Atlantique)

  • 18th May 2021: MLDADS 2021 Webinar - Alban Farchi and Dennis Knol

  • 25th May 2021: MLDADS 2021 Webinar - Blas Ko and Ahn Khoa 

  • 1st June 2021: MLDADS 2021 Webinar - Pasquale de Luca and Muzammil Hussain Rammay

  • 8th June 2021: Data-driven optimization for systems engineering - by Antonio Del Rio Chanona (Imperial College London)

  • 15th June 2021: Learning Physical Simulations with Graph Networks - by Álvaro Sánchez González (DeepMind)

  • 22nd June 2021: Generative model-based super-resolution and quality control for cardiac segmentation - Shuo Wang (Fudan University)

  • 29th June 2021: SliceGAN: Generating 3D structures from a 2D slice with GAN-based dimensionality expansion - Steven Kench (Imperial College London)

  • 14th September 2021: Coupling of deep neural networks and physical invariants for turbulent flow surrogate modeling - Didier Lucor (CNRS, Paris-Saclay University) 

  • 21st September 2021: Physical inductive biases for learning simulation and scientific discovery - Peter Battaglia (DeepMind)

  • 28th September 2021: The importance of discretization drift in deep learning - Mihaela Rosca (DeepMind)

  • 12th October 2021: Martian Atmosphere Reconstruction through a Long Short-Term Memory Network - Davide Amato (ICL)

  • 26th October 2021: Adversarial Perturbations in the wild and their applications - Stefano Marrone (UNINA) 

  • 2nd November 2021: Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels - Yi Zhou (Adobe research)

  • 9th November 2021: Exactly solvable models for high-dimensional machine learning problems - Bruno Loureiro (EPFL)

  • 16th November 2021: Data-driven and learning-based approaches for the modeling, forecasting and reconstruction of geophysical dynamics - Said Ouala (IMT Atlantique)

  • 23rd November 2021: Statistical physics of stochastic gradient descent - Francesca Mignacco (EPFL) 

  • 30th November 2021: Assisting Sampling with Learning: Adaptive Monte Carlo with Normalizing Flows - Marylou Gabrié (NYU/Flatiron Institute) 

  • 7th December 2021: Bridging Data Assimilation and Deep Learning - Arthur Filoche (Sorbonne University)

2022
  • 11th January 2022: OceanIA: AI and machine learning for understanding the ocean and climate change - Luis Martí (Inria Chile)

  • 18th January 2022: Machine Learning for Scientific Discovery, with Examples in Fluid Mechanics - Steven Brunton (University of Washington)

  • 25th January 2022: Twitter as an alternative data source for international migration studies - Jisu Kim (Max Planck Institute)

  • 1st February 2022: The Future of Finance and Economics: The crossroad between Models, Data, and Artificial Intelligence - Irena Vodenska (Boston University)

  • 8th February 2022: The frontier of Simulation-Based Inference - Gilles Louppe (University of Liege)

  • 15th February 2022: Bridging the gap between simulations and real data - domain adaptation for deep learning in physics and astronomy - Aleksandra Ćiprijanović (FNAL)

  • 22nd February 2022: Useful Inductive Biases for Deep Learning in Molecular Science - Max Welling (University of Amsterdam, Microsoft Research)

  • 1st March 2022: Predicting material properties with the help of machine learning - Bingqing Cheng (Institute of Science and Technology Austria)

  • 8th March 2022: Graph Neural Networks for Charged Particle Reconstruction at the Large Hadron Collider - Savannah Thais (Princeton University)

  • 15th March 2022: The importance of vegetation and drought for global fire prediction - Alexander Kuhn-Regnier (Imperial College London)

  • 29th March 2022: Gaussian processes, missing data, and optimal transport - Felipe Tobar (Universidad de Chile)

  • 5th April 2022: Bayesian Inference in Physics-Based Nonlinear Flame Models - Maximilian Croci (University of Cambridge)

  • 10th May 2022: Coreo-Graph - Mariel Pettee (Lawrence Berkeley National Laboratory)

  • 17th May 2022: Tackling Fairness, Change, and Polysemy in Word Embeddings - Felipe Bravo (Universidad de Chile)

  • 24th May 2022: Augmenting the prediction of extubation failure using measures of complexity - Sandip Varkey George (UCL)

  • 31st May 2022: Physics-Informed Deep Learning: Learning from Small Data - Lu Lu (University of Pennsylvania )