Research work and relevant papers by our team

M²LInES research publications

If you are interested in understanding how M²LInES is using machine learning to improve climate models, we have developed an educational JupyterBook Learning Machine Learning for Climate modeling with Lorenz 96. This JupyterBook describes the key research themes in M²LInES, through the use of a simple climate model and machine learning algorithms. You can run the notebooks yourself, contribute to the development of the JupyterBook or let us know what you think on GitHub


📙 Chemke R, Yuval J. Human-induced weakening of the Northern Hemisphere tropical circulation Nature. 2023

📘 Otness K, Zanna L, Bruna J. Data-driven multiscale modeling of subgrid parameterizations in climate models. arXiv:2303.17496. Preprint submitted to ICLR Workshop on Climate Change AI. 2023

📄 Falasca F, Brettin A, Zanna L, Griffies SM, Yin J, Zhao M. Exploring the non-stationarity of coastal sea level probability distributions. Preprint submitted to EDS. 2023

📄 Perezhogin P, Fernandez-Granda C, Zanna L. Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model. Preprint submitted to JAMES. 2023

📙 Ross AS, Li Z, Perezhogin P, Fernandez-Granda C, Zanna L. Benchmarking of machine learning ocean subgrid parameterizations in an idealized model . JAMES. 2023


📄 Shamekh S, Lamb K.D, Huang Y, Gentine P. Implicit learning of convective organization explains precipitation stochasticity In review. 2022

📙 Christensen H, Zanna L. Parametrization in Weather and Climate Models. Oxford Research Encyclopedia of Climate Science. 2022

📘 Liu S, Kaku A, Zhu W, Leibovich M, Mohan S, Yu B, Huang H, Zanna L, Razavian N, Niles-Weed J, Fernandez-Granda C. Deep Probability Estimation, Proceedings of the 39th International Conference on Machine Learning, PMLR 162:13746-13781, 2022.

📙 Loose N, Abernathey R, Grooms I, Busecke J, Guillaumin A, Yankovsky E, Marques G, Steinberg J, Ross AS, Khatri H, Bachman S, Zanna L, Martin P. GCM-Filters: A Python Package for Diffusion-based Spatial Filtering of Gridded Data., Journal of Open Source Software 7(70), p.3947. 2022

📙 Frezat H, Le Sommer J, Fablet R, Balarac G, Lguensat R. A posteriori learning for quasi-geostrophic turbulence parametrization JAMES. 2022

📙 Zampieri L, Arduini G, Holland M, Keeley S, Mogensen KS, Tietsche S. A machine learning correction model of the clear-sky bias over the Arctic sea ice in atmospheric reanalyses J Earth and Space Science Open Archive. 2022 (preprint)

📄 Chen L, Bruna J. On Gradient Descent Convergence beyond the Edge of Stability. arXiv preprint arXiv:2206.04172, 2022 (preprint)

📄 Bhouri MA, Gentine P. History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz ‘96 arXiv preprint arXiv:2210.14488 (preprint)


📄 Beucler T, Pritchard M, Yuval J, Gupta A, Peng L, Rasp S, Ahmed F, O’Gorman PA, Neelin JD, Lutsko NJ, Gentine P. Climate-Invariant Machine Learning arXiv preprint arXiv:2112.08440. 2021 (preprint)

📄 Wang P, Yuval J, O’Gorman PA. Non-local parameterization of atmospheric subgrid processes with neural networks arXiv preprint arXiv:2201.00417. 2022 (preprint)

📄 Yuval J, O’Gorman PA. Neural-network parameterization of subgrid momentum transport in the atmosphere. J Earth and Space Science Open Archive (preprint)

📙 Guillaumin A, Zanna L. Stochastic Deep Learning parameterization of Ocean Momentum Forcing. Journal of Advances in Modeling Earth Systems 2021.

Relevant publications by our team