Catégorie : journal club

Next meetings

• [13-05-2024] « Using Deep Learning for Restoration of Precipitation Echoes in Radar Data » Lepetit et al. 2021 https://www.researchgate.net/publication/349458411_Using_Deep_Learning_for_Restoration_of_Precipitation_Echoes_in_Radar_Data discussion led by Aymeric Chazottes

Past meetings

• [22-02-2024] « GenCast: Diffusion-based ensemble forecasting for medium-range weather » Price et al. 2023 https://arxiv.org/abs/2312.15796 discussion led by David Landry
• [24-01-2024] « ACE: A fast, skillful learned global atmospheric model for climate prediction » Watt-Meyer et al. 2023 https://arxiv.org/abs/2310.02074 discussion led by Olivier Boucher
• [21-12-2023] « Neural General Circulation Models » Kochkov et al. 2023 https://arxiv.org/abs/2311.07222  discussion led by Louis Thiry
• [05-07-2023] « Attention is all you need » Vaswani et al. 2017 https://arxiv.org/abs/1706.03762 Discussion on Transformers and Vision Transformers led by Germain Benard
• [23-02-2023] « GraphCast: Learning skillful medium-range global weather forecasting » Lam et al. 2022 https://arxiv.org/abs/2212.12794 Discussion led by Redouane Lguensat
• [26-01-2023] How to Calibrate a Dynamical System With Neural Network Based Physics? https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022GL097872 Discussion led by Blanka Balogh
• [23-06-2022] ​ Inferring causation from time series in Earth system sciences (Runge et al. 2019) https://www.nature.com/articles/s41467-019-10105-3 Discussion led by: Homer Durand
• [18-11-2021] Learning to Simulate Complex Physics with Graph Networks (Sanchez-Gonzalez et al. 2020) http://proceedings.mlr.press/v119/sanchez-gonzalez20a/sanchez-gonzalez20a.pdf ICLR 2020 paper
  Discussion led by: Alex Ayet (CNRS, Gipsa-Lab)
• [21-10-2021] Data-driven discovery of coordinates and governing equations (Champion et al. 2019) https://www.pnas.org/content/116/45/22445.short
  Disucssion led by: V. Balaji
• [17-06-2021] ​ Using machine learning to predict statistical properties of non-stationary dynamical processes: System climate,regime transitions, and the effect of stochasticity (Patel et al. 2021) https://aip.scitation.org/doi/10.1063/5.0042598
  Discussion led by: Julien Brajard
• [29-05-2020] ​ Improving El Nino Forecasts with Graph Neural Networks (Cachay et al. 2021) https://arxiv.org/abs/2104.05089
  Discussion led by: Joana Roussillon
• [29-04-2020] Machine learning accelerated computational fluid dynamics (Kochkov et al. 2021) https://arxiv.org/abs/2102.01010
  Discussion led by: Hugo Frezat
• [18-03-2020] Using machine learning to correct model error in data assimilation and forecast applications (Farchi et al. 2020) https://arxiv.org/abs/2010.12605
  Discussion led by: Alban Farchi
• [18-02-2020] Taking climate model evaluation to the next level (Eyring et al. 2019) https://www.nature.com/articles/s41558-018-0355-y
  Discussion led by: Pierre Le Bras
• [17-12-2020] DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations (Barth et al. 2020) https://gmd.copernicus.org/articles/13/1609/2020/
  Discussion led by: Anastase Charantonis
• [26-11-2020] Process-based climate model development harnessing machine learning: II. model calibration from single column to global (Hourdin et al. 2020) https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2020MS002225 
  Discussion led by: Frederic Hourdin
• [15-10-2020] ExGAN: Adversarial Generation of Extreme Samples (Bhatia et al. 2020) Paper: https://arxiv.org/pdf/2009.08454v1.pdf
  Discussion led by: Maxime Beauchamp
• [17-09-2020]  Process-based climate model development harnessing machine learning: I. a calibration tool for parameterization improvement (Couvreux et al. 2020)
  Paper: https://www.essoar.org/doi/10.1002/essoar.10503597.1
  Discussion led by: Redouane Lguensat
• [16-07-2020] A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets (Anantrasirichaia et al. 2019)
  Paper:
  https://arxiv.org/pdf/1905.07286.pdf
  Discussion led by: Sophie Giffard-Roisin
• [18-06-2020] Up to two billion times acceleration of scientific simulations with deep neural architecture search (Kasim et al. 2020)
  Papers:
  https://arxiv.org/pdf/2001.08055.pdf
  Discussion led by: Julie Deshayes
• [28-05-2020] Machine learning and the physical sciences (Carleo et al. 2019) + Deep learning and process understanding for data-driven Earth system science (Reichstein et al. 2019) Papers:
  https://arxiv.org/abs/1903.10563 + https://www.nature.com/articles/s41586-019-0912-1
  Discussion led by: Maike Sonnewald
• [16-04-2020] Universal Differential Equations for Scientific Machine Learning (Rackauckas et al. 2020)
  Paper: https://arxiv.org/pdf/2001.04385.pdf 
  Discussion led by: Redouane Lguensat
• [19-03-2020] WeatherBench: A benchmark dataset for data-driven weather forecasting by S. Rasp, P.D. Dueben, S. Scher, J.A. Weyn, S. Mouatadid and N. Thuerey (2020)
  Paper: https://arxiv.org/abs/2002.00469
  Discussion led by: Julien Le Sommer
• [27-02-2020] Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence (George et al. 2020)
  Paper: https://eartharxiv.org/erhy2/
  Discussion led by: Julie Deshayes

For any question/suggestion please contact Redouane Lguensat: rlguensat at ipsl dot fr