In the climate system, extreme events or transitions between climate attractors are of primarily importance for understanding the impact of climate change and designing adaptation and mitigation strategies. Recent extreme heat waves with huge impact, or periods of very low production of renewable energy in the electricity system are striking examples. However, a key challenge is the lack of data, because these events are too rare and realistic models are too complex. This lack of data issue drastically challenges any available approaches either based on physics or statistics.

I will discuss new algorithms and theoretical approaches, based on rare event simulations, emulators of climate models, and machine learning for stochastic processes, which we have specifically designed for the prediction of the probability of the extreme event to occur, and their dynamics. To illustrate the performance of these tools, I will discuss results for the study of midlatitude extreme heat waves and the extremes of renewable energy production in relation with the resilience of the electricity system.

I will also briefly outline the use of large deviation theory to describe the statistics of rare fluctuation in kinetic theory with applications to the classical kinetic theories and wave turbulence theory with ocean applications.

References:

1. A. Lancelin, A. Wikner, L. Dubus, C. Le Priol, D. S. Abbot, F. Bouchet, P. Hassanzadeh and J. Weare, 2025, AI-boosted rare event sampling to characterize extreme weather, arXiv:2510.27066, [pdf].
2. F. Ragone, J. Wouters, and F. Bouchet, 2018, Computation of extreme heat waves in climate models using a large deviation algorithm, Proceedings of the National Academy of Sciences, vol 115, no 1, pages 24-29, doi.org/10.1073/pnas.1712645115, and arXiv:1709.03757, [pdf].
3. V. Mascolo, A. Lovo, C. Herbert, and F. Bouchet, 2024, Gaussian Framework and Optimal Projection of Weather Fields for Prediction of Extreme Events, arXiv:2405.20903, [pdf].
4. A. Lovo, A. Lancelin, C. Herbert, and F. Bouchet, 2024, Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwaves, arXiv:2410.00984, [pdf].
5. G. Miloshevich, B. Cozian, P. Abry, P. Borgnat, and F. Bouchet, 2023, Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data, Phys. Rev. Fluids, 8, 040501, doi.org/10.1103/PhysRevFluids.8.040501 and arXiv:2208.00971, [pdf].
6. B. Cozian, C. Herbert, and F. Bouchet, 2023, Assessing the Probability of Extremely Low Wind Energy Production in Europe at Sub-seasonal to Seasonal Time Scales, Environmental Research Letters, 2024, vol. 19, no 4, p. 044046, doi.org/10.1088/1748-9326/ad35d9, and arXiv:2311.13526, [pdf].
7. Y. Onuki, J. Guioth, and F. Bouchet, 2023, Dynamical large deviations for an inhomogeneous wave kinetic theory: linear wave scattering by a random medium, Ann. Henry. Poincaré, doi.org/10.1007/s00023-023-01329-7, and arXiv:2301.03257, [pdf].