diff --git a/content/news/2607AGU.md b/content/news/2607AGU.md new file mode 100644 index 00000000..37bb75cc --- /dev/null +++ b/content/news/2607AGU.md @@ -0,0 +1,22 @@ +--- +date: 2026-07-01T09:29:16+10:00 +title: " AGU 2026 — Save the Date & Submit Your Abstracts!" +heroHeading: '' +heroSubHeading: '' +heroBackground: '' +thumbnail: 'images/news/2607AGU.png' +images: ['images/news/2607AGU.png'] +link: 'https://agu.confex.com/agu/agu26/prelim.cgi/Home/0' +--- + +AGU26 is coming to San Francisco, December 7–11, and abstract submissions are open until **August 5th**. We encourage the community to consider submitting to the following **sessions co-convened by M²LInES members**: + +- Developments in Machine Learning Across Earth System Modeling: Subgrid-Scale Parameterizations, Emulation, and Hybrid Modeling (co-convened by **Sara Shamekh**) + +- Subseasonal to Seasonal Tropical Variability: Observations, Modeling, Processes, and Global Impacts (co-convened by **Danni Du**) + +- Emerging Machine Learning Approaches for Ecosystem Process Understanding and Knowledge Discovery (co-convened by **Pierre Gentine**) + +- Climate Tipping Points and their Impacts (co-convened by **Pierre Gentine**) + +**Submit your abstract [here](https://agu.confex.com/agu/agu26/prelim.cgi/Home/0) by August 5th 23:59pm EDT** \ No newline at end of file diff --git a/content/news/2607Ars.md b/content/news/2607Ars.md new file mode 100644 index 00000000..25ebd21c --- /dev/null +++ b/content/news/2607Ars.md @@ -0,0 +1,12 @@ +--- +date: 2026-07-01T09:29:16+10:00 +title: " M²LInES in the News: Ars Technica article" +heroHeading: '' +heroSubHeading: '' +heroBackground: '' +thumbnail: 'images/news/2607ArsTechnica.png' +images: ['images/news/2607ArsTechnica.png'] +link: 'https://arstechnica.com/science/2026/06/the-weather-and-climate-science-ai-revolution-isnt-revolutionary/' +--- + +Ars Technica recently **[featured](https://arstechnica.com/science/2026/06/the-weather-and-climate-science-ai-revolution-isnt-revolutionary/)** the growing role of AI in weather and climate science, **highlighting the work of Laure Zanna and the M²LInES project** in developing physics-informed machine learning approaches for climate modeling. \ No newline at end of file diff --git a/content/news/2607Nasser.md b/content/news/2607Nasser.md new file mode 100644 index 00000000..dd5beb02 --- /dev/null +++ b/content/news/2607Nasser.md @@ -0,0 +1,12 @@ +--- +date: 2026-07-01T09:29:16+10:00 +title: " Design principles for stable and generalizable data-driven discretizations for solving linear hyperbolic conservation laws" +heroHeading: '' +heroSubHeading: '' +heroBackground: '' +thumbnail: 'images/news/2607Nasser.png' +images: ['images/news/2607Nasser.png'] +link: 'https://doi.org/10.48550/arXiv.2606.17497' +--- + +Antoine Nasser and Alistair Adcroft investigate how machine learning can be used to develop **stable and accurate numerical schemes for solving the linear advection equation**. Their **[study](https://doi.org/10.48550/arXiv.2606.17497)** identifies the key factors governing the performance of data-driven finite-volume methods, including network architecture, training data, and normalization strategies. They show that data-driven reconstructions based on cell averages are shape-specific, limiting their ability to generalize across different classes of solutions. They introduce a machine-learned flux limiter that improves shape preservation relative to widely used classical schemes and demonstrate that training on polynomial profiles yields stable, high-order accurate discretizations. Overall, the work provides **practical guidelines for designing robust and generalizable machine-learning-based numerical methods for scientific computing.** \ No newline at end of file diff --git a/content/news/2607Samudra2.md b/content/news/2607Samudra2.md new file mode 100644 index 00000000..4fd536af --- /dev/null +++ b/content/news/2607Samudra2.md @@ -0,0 +1,24 @@ +--- +date: 2026-07-01T09:29:16+10:00 +title: " Samudra 2: Supercomputer Ocean Modeling on a Single GPU!" +heroHeading: '' +heroSubHeading: 'Samudra 2: Scaling Ocean Emulators across Resolutions' +heroBackground: '' +thumbnail: 'images/news/2607Samudra2.png' +images: +link: 'https://doi.org/10.48550/arXiv.2606.02610' +--- + +Yuan Yuan and collaborators from M²LInES and Open Athena have unveiled **[Samudra 2](https://doi.org/10.48550/arXiv.2606.02610)**, a next-generation neural ocean emulator that collapses massive supercomputer workloads down to a single GPU. Running **100x to 1000x faster** than traditional numerical models, it successfully scales to fine resolutions capable of capturing critical mesoscale eddies and sharp currents like the Gulf Stream without drifting or "blowing up" over multi-year simulations. + + + +By slashing deep-ocean errors by **7–10×** and maintaining realistic physics, Samudra 2 turns a major computational bottleneck into an opportunity for massive ensemble modeling. This open-source breakthrough shifts climate science from rationing a few scenarios to running hundreds of plausible futures, paving the way for low-cost, decision-grade forecasting in shipping, energy, and sea-level rise. Read the full announcement in our **[latest blog post](https://medium.com/@lz1955/samudra-2-a-fast-cheap-ai-ocean-model-now-at-the-scale-that-matters-b37883c62d51)**, explore the **[project page and rollout demo](https://m2lines.github.io/Samudra/docs/)**, grab the **[code on GitHub](https://github.com/m2lines/Samudra)**, or just run it **using the weights on [Hugging Face](https://huggingface.co/M2LInES/Samudra2)**. + + + +If you are interested in developing these models, [join our growing team at M²LInES](/jobs)! + +{{< youtube Vs8fdoVlwis >}} + +
\ No newline at end of file diff --git a/content/news/Newsletters/_index.md b/content/news/Newsletters/_index.md index 21ec4c5d..b0bf8bbf 100644 --- a/content/news/Newsletters/_index.md +++ b/content/news/Newsletters/_index.md @@ -12,6 +12,8 @@ tags: ### 2026 +* 07/01/2026 - [M²LInES newsletter - July 2026](https://mailchi.mp/1e6b380a8003/m2lines-july2026) + * 06/02/2026 - [M²LInES newsletter - June 2026](https://mailchi.mp/25cfd79a0287/m2lines-june2026) * 05/01/2026 - [M²LInES newsletter - May 2026](https://mailchi.mp/0ea31f7e9316/m2lines-may2026) diff --git a/content/publications/_index.md b/content/publications/_index.md index 52da2a27..36149305 100644 --- a/content/publications/_index.md +++ b/content/publications/_index.md @@ -14,6 +14,17 @@ You can also check all our publications on our **[Google Scholar profile](https: DOI icon M²LInES funded research ### 2026 +
+
+ +
+

+ DOI icon + Antoine-Alexis Nasser, Alistair Adcroft
+ Design principles for stable and generalizable data-driven discretizations for solving linear hyperbolic conservation laws
+ GRL DOI:10.48550/arXiv.2606.17497 +

+
diff --git a/static/images/news/2607AGU.png b/static/images/news/2607AGU.png new file mode 100644 index 00000000..18553f1c Binary files /dev/null and b/static/images/news/2607AGU.png differ diff --git a/static/images/news/2607ArsTechnica.png b/static/images/news/2607ArsTechnica.png new file mode 100644 index 00000000..04d2fc04 Binary files /dev/null and b/static/images/news/2607ArsTechnica.png differ diff --git a/static/images/news/2607Nasser.png b/static/images/news/2607Nasser.png new file mode 100644 index 00000000..0c8f2e72 Binary files /dev/null and b/static/images/news/2607Nasser.png differ diff --git a/static/images/news/2607Samudra2.png b/static/images/news/2607Samudra2.png new file mode 100644 index 00000000..6ab23c8a Binary files /dev/null and b/static/images/news/2607Samudra2.png differ