IMT-Atlantique M2 internship: Precursors of extremes from data

11 Janvier 2024

---

Catégorie : Stagiaire

---

IMT Atlantique M2 internship: Artificial Intelligence for the Representation of Precursors of Extreme Events in Ocean-Atmosphere and Climate Systems

Introduction

Extreme events are observed in a variety of Ocean, Atmosphere, and Climate (OAC) systems. Examples include powerful hurricanes, prolonged droughts, and severe terrestrial and marine heatwaves. These events are associated with abrupt changes in the state of the system and often cause unfortunate humanitarian, environmental, and financial impacts. These events, which are often characterized by their rarity and intensity, pose significant challenges to our understanding of Earth’s dynamics and to our ability to predict, mitigate, and adapt to their consequences.

Understanding the drivers and mechanisms responsible for the occurrence of extreme events is crucial. This knowledge is essential for developing effective strategies to predict, mitigate, and adapt to their impacts. This question is highly challenging, as extreme events in Ocean-Atmosphere-Climate (OAC) systems result from the complex nonlinear interaction of various physical processes within a high-dimensional dynamic system. In this project, our goal is to explore Artificial Intelligence techniques for identifying regions of instabilities in complex dynamical systems. We concentrate on systems governed by differential equations [1] and aim to find a mapping that reveals instability regions responsible for the emergence of extreme events [2].

Workplan

• Study state-of-the-art on AI for extreme events in OAC systems.
• Implementation of benchmark models. Here, we focus on systems governed by differential equations and we consider various types of instabilities responsible for the formation of extreme events (multiscale, chaotic, stochastic, etc.).
• Definition of the AI-based mapping and training criteria.
• Implementation of the overall framework.
• Evaluation, tuning, and validation.

Profile of the candidate

• Enrolled in Master 2 or in the last year of an engineering school.
• Knowledge in Machine Learning, Deep Learning, and generative models (e.g., variational autoencoders).
• A good understanding of the use of Deep Learning Frameworks (PyTorch, TensorFlow, JAX).
• Prior experience in research is highly advantageous.

Documents to be submitted

Please send following documents in a single pdf page with the title of Application-Internship-Odyssey-IA4Extremes' for evaluations to: said.ouala@imt-atlantique.frronan.fablet@imt-atlantique.fr

• Curriculum Vitae.
• Motivation letter (max 1 page).
• Current diploma and transcripts.
• Recommendation letters.

Application deadlines, selection process and start of work

• Application deadline is 31 January 2024.
• Selection to be planned from 2nd to 5th february 2024.
• Start of work flexible, between March/April 2024.

Further questions

Further questions can be addressed to:

• Said Ouala, said.ouala@imt-atlantique.fr,
• Ronan Fablet, ronan.fablet@imt-atlantique.fr

About the hosting organisation

IMT Atlantique is internationally recognized for the quality of its research, is a leading French technological university under the supervision of the Ministry of Industry and Digital Technology. IMT Atlantique maintains privileged relationships with major national and international industrial partners, as well as with a dense network of SMEs, start-ups, and innovation networks. With 290 permanent staff, 2,200 students, including 300 doctoral students, IMT Atlantique produces 1,000 publications each year and raises 18€ million in research funds.

References

[1] Farazmand, Mohammad, and Themistoklis P. Sapsis. "Extreme events: Mechanisms and prediction." Applied Mechanics Reviews 71.5 (2019): 050801.

[2] Sapsis, Themistoklis P. "Statistics of extreme events in fluid flows and waves." Annual Review of Fluid Mechanics 53 (2021): 85-111.