We are hereby re-transmiting the Journal Club news:
This is an announcement of a ‘Journal Club’ on the subject of ‘machine learning’ (ML) methods and their potential application in Earth System modeling (ESM). We will read together (with some imagination the name of the journal club can be pronounced ‘ensemble’!) some of the key papers in this nascent domain, to give ourselves ideas and inspiration on how to integrate these methods in our work, to find a common language between the ESM and ML disciplines, between theory and practice, between idealized systems and the Earth system.
The rules of the game are: someone picks an article where she would like to lead a discussion. To be clear, ‘leading’ doesn’t mean explaining the whole paper: everyone is supposed to have read the paper beforehand, and the discussion will cover points in the paper that aren’t clear, potential flaws and holes, and ideas on how to continue down the path ourselves.
I will lead the first one-hour session, and hope that others will volunteer to lead future ones! It will be on a monthly schedule, every third Thursday, at 14h.
Thus the first is scheduled for 21 February 2019. There is a room reserved at Jussieu at METIS (Campus Pierre et Marie Curie – Salle Henry Darcy – 3e étage – couloir 46-56) and a visio as well to allow participation from Paris and Saclay campuses. Details, see below.
We will begin with these two articles:
– Schneider et al 2017: Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High‐Resolution Simulations. https://agupubs.onlinelibrary.wiley.com/doi/full/10.1002/2017GL076101
– Bolton and Zanna 2019: Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization. https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018MS001472
Hope to see you on the 21st. To have some idea of the level of interest, please drop me a note… but please don’t ‘reply all’ !