Pre-submission enquiry: "Learning Machine Learning with Lorenz-96"

[Ryan Abernathey]

Hello JOSE editors! Thanks for your work on this fantastic open journal! 👏

I am making a pre-submission enquiry. Our team in the M²LInES - Multiscale Machine Learning In Coupled Earth System Modeling project has put together a pedagogically focused Jupyter Book entitled Learning Machine Learning with Lorenz-96.

The goal of this book is to conceptualize the problems associated with climate models within a simple and computationally accessible framework. We will introduce the readers to climate modeling by using a simple tool, the Lorenz [L96] two-timescale model. We discuss the numerical aspects of the L96 models, the parameterizations of small-scale processes, and simple data assimilation problems. We will then use the L96 results to learn subgrid parameterizations with machine learning, and then test the parameterizations offline and online, with a focus on the interpretability of the results.

The book consists of roughly a dozen Jupyter notebooks. We feel that this material will have broad value for both climate scientists interested in machine learning and data scientists interested in climate.

Based on my reading of the JOSE scope, it seems like this could be a good fit for JOSE. We are probably a few weeks away from submission ready, but I wanted to check whether you agree that this would be in scope for JOSE.

Thanks for your time.

[Lorena A. Barba]

hi @rabernat – sincere apologies, but it turns out I wasn't "watching" this repository and have not come poking here in a long time (I had it set to "only when @-mentioned"... I changed it now).

Is your team still interested in exploring a JOSE publication for this work?