Journal Club

The AI4Climate team organizes regular journal club meetings to discuss recent papers in AI and climate science.

Meetings

2024

• May 13 | Using Deep Learning for Restoration of Precipitation Echoes in Radar Data
  Lepetit et al. (2021) — Led by Aymeric Chazottes

• February 22 | GenCast: Diffusion-based ensemble forecasting for medium-range weather
  Price et al. (2023) — Led by David Landry

• January 24 | ACE: A fast, skillful learned global atmospheric model for climate prediction
  Watt-Meyer et al. (2023) — Led by Olivier Boucher

2023

• December 21 | Neural General Circulation Models
  Kochkov et al. (2023) — Led by Louis Thiry

• July 5 | Attention is all you need
  Vaswani et al. (2017) — Led by Germain Benard
  Discussion on Transformers and Vision Transformers

• February 23 | GraphCast: Learning skillful medium-range global weather forecasting
  Lam et al. (2022) — Led by Redouane Lguensat

• January 26 | How to Calibrate a Dynamical System With Neural Network Based Physics?
  Led by Blanka Balogh

2022

• June 23 | Inferring causation from time series in Earth system sciences
  Runge et al. (2019) — Led by Homer Durand

2021

• November 18 | Learning to Simulate Complex Physics with Graph Networks
  Sanchez-Gonzalez et al. (2020) — Led by Alex Ayet (CNRS, Gipsa-Lab)

• October 21 | Data-driven discovery of coordinates and governing equations
  Champion et al. (2019) — Led by V. Balaji

• June 17 | Using machine learning to predict statistical properties of non-stationary dynamical processes
  Patel et al. (2021) — Led by Julien Brajard

• May 29 | Improving El Nino Forecasts with Graph Neural Networks
  Cachay et al. (2021) — Led by Joana Roussillon

• April 29 | Machine learning accelerated computational fluid dynamics
  Kochkov et al. (2021) — Led by Hugo Frezat

• March 18 | Using machine learning to correct model error in data assimilation and forecast applications
  Farchi et al. (2020) — Led by Alban Farchi

• February 18 | Taking climate model evaluation to the next level
  Eyring et al. (2019) — Led by Pierre Le Bras

2020

• December 17 | DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations
  Barth et al. (2020) — Led by Anastase Charantonis

• November 26 | Process-based climate model development harnessing machine learning: II. model calibration from single column to global
  Hourdin et al. (2020) — Led by Frederic Hourdin

• October 15 | ExGAN: Adversarial Generation of Extreme Samples
  Bhatia et al. (2020) — Led by Maxime Beauchamp

• September 17 | Process-based climate model development harnessing machine learning: I. a calibration tool for parameterization improvement
  Couvreux et al. (2020) — Led by Redouane Lguensat

• July 16 | A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets
  Anantrasirichaia et al. (2019) — Led by Sophie Giffard-Roisin

• June 18 | Up to two billion times acceleration of scientific simulations with deep neural architecture search
  Kasim et al. (2020) — Led by Julie Deshayes

• May 28 | Machine learning and the physical sciences + Deep learning and process understanding for data-driven Earth system science
  Carleo et al. (2019) + Reichstein et al. (2019) — Led by Maike Sonnewald

• April 16 | Universal Differential Equations for Scientific Machine Learning
  Rackauckas et al. (2020) — Led by Redouane Lguensat

• March 19 | WeatherBench: A benchmark dataset for data-driven weather forecasting
  Rasp et al. (2020) — Led by Julien Le Sommer

• February 27 | Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence
  George et al. (2020) — Led by Julie Deshayes

History

The journal club was created by V. Balaji and Julie Deshayes in 2020 during V. Balaji’s MOPGA stay at IPSL

Organisers:

• Redouane Lguensat (2020 - now)