Events 2023

📍 Machine Learning & Climate Day (2023)

Overview

This event, co-organised by EDF R&D and the French ENBIS network
(frENBIS), is part of our ongoing efforts to promote statistics and machine learning methods within industry and business.

The morning session was dedicated to a training course on Generalized Additive Models (GAMs), delivered by
Matteo Fasiolo, Senior Lecturer at the School of Mathematics – Statistical Science of the University of Bristol, and author of the
qGAM and mgcViz packages.

The theoretical foundations of GAMs were presented, together with practical illustrations in R (notebooks).

The afternoon session featured talks from academia and industry, showcasing applications of machine learning to climate and environmental modelling.

🧭 Practical Information

  • 📍 Venue: EDF Lab Saclay
  • 📅 Date: Thursday, October 19, 2023
  • 💰 Registration: free of charge, mandatory registration (online form)

🕒 Programme

Morning – Training Session (GAMs)

Time Content
09:00 – 09:30 Welcome coffee
09:30 – 11:00 Generalized Additive Models (GAMs) – Lecture 1
11:00 – 11:15 Break
11:15 – 12:30 Generalized Additive Models (GAMs) – Lecture 2

Lunch break

Afternoon – Climate and Environmental Applications

Time Title Speaker
13:45 – 14:25 Near real-time global power production data and implications of climate extremes Philippe Ciais, Research Director, LSCE
14:25 – 15:05 Leveraging AI for weather prediction at Météo-France: a review of ongoing activities Laure Reynaud, Researcher at CNRM (Météo-France / CNRS)
15:05 – 15:45 How to aggregate climate data to predict crop yield: an application to soybean Mathilde Chen, Postdoctoral Fellow, MIA Paris-Saclay
15:45 Coffee & networking

🎯 Scientific Objectives

The objectives of this event were to:

  • present modern statistical tools (GAMs) for the analysis of complex data,
  • illustrate practical applications of machine learning to climate, energy, and agriculture,
  • foster interaction and collaboration between researchers, engineers, and practitioners.

Special attention was given to challenges related to:

  • weather and climate prediction,
  • the impact of extreme events,
  • the exploitation of environmental data for decision support.