Resources

Open Storage Network Pod

M²LInES has an Open Storage Network (OSN) Pod! What can you get out of the Pod as a member of the team:

• A project for a specific bucket (authenticated or public) to work with your team
• Move data (needs LEAP DCT team admin) to the publication bucket (m2lines-pubs) before publishing a paper.
• Ingest publicly available datasets into Analysis Ready Cloud Optimized formats. Start by adding an issue here and work with the LEAP DCT on the recipe. More info in the docs You can find the relevant guide to the pod here

Non-members can access publicly available data from our team. As with all the OSN Pod, 20% of our space is reserved for public use.

Learning Machine Learning with Lorenz-96

The M²LInES team is proud to share this article and Jupyter Book published in the Journal of Open Science Education (JOSE) and led by Dhruv Balwada. Developed by our team, it aims to introduce Machine Learning (ML) methods to climate scientists and also climate modeling to machine learning experts. The book presents a wide range of ML applications for climate modeling, focusing on hybrid AI+Physics methods using the Lorenz-96 model. We hope this book can be used as a pedagogical tool for self-learning, a reference manual, or for teaching modules in an introductory class on ML or hybrid climate modeling.

🚧 Under Development 🚧