m2lines · johannag126 · May 4, 2026 · May 4, 2026
diff --git a/content/news/2604Gregory.md b/content/news/2604Gregory.md
@@ -0,0 +1,12 @@
+---
+date: 2026-04-01T09:29:16+10:00
+title: "FloeNet"
+heroHeading: ''
+heroSubHeading: 'FloeNet: A mass-conserving global sea ice emulator that generalizes across climates'
+heroBackground: ''
+thumbnail:  'images/news/2604FloeNet.gif'
+images: ['images/news/2604FloeNet.gif']
+link: 'https://doi.org/10.48550/arXiv.2603.12449'
+---
+
+**Will Gregory** et al. introduce **[FloeNet](https://doi.org/10.48550/arXiv.2603.12449), a machine-learning emulator trained on the GFDL global sea ice model (SIS2)** to reproduce key sea-ice and snow-on-sea-ice processes while conserving mass. The model emulates 6-hour tendencies related to ice and snow growth, melt, and advection. Trained on reanalysis-forced simulations, FloeNet was tested across different climate states, including pre-industrial and an increasing CO₂ scenario. It accurately **reproduces sea-ice mean state, trends, and interannual variability, outperforming non-conservative approaches.** FloeNet also captures the balance between thermodynamic and dynamic responses to forcing and reproduces coupling-related variables such as ice-surface temperature and ocean salt fluxes. These results suggest strong potential for improving the representation of polar processes in climate emulators.
diff --git a/content/news/2604Liu.md b/content/news/2604Liu.md
@@ -0,0 +1,12 @@
+---
+date: 2026-04-01T09:29:16+10:00
+title: "Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems"
+heroHeading: ''
+heroSubHeading: 'Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems'
+heroBackground: ''
+thumbnail:  'images/news/2604Liu.png'
+images: ['images/news/2604Liu.png']
+link: 'https://doi.org/10.48550/arXiv.2603.17750'
+---
+
+Autoregressive neural surrogate models can dramatically accelerate simulations of dynamical systems, but they often suffer from error accumulation over long time horizons. This **[work](https://doi.org/10.48550/arXiv.2603.17750), led by Qi Liu, introduces a unifying framework** that formalizes the trade-off between short-term accuracy and long-term consistency, which most previous approaches handled heuristically. Building on this, the authors propose a **new hyperparameter-free method: Self-refining Neural Surrogate (SNS)**, based on conditional diffusion. SNS can iteratively refine its own predictions or enhance existing models, **delivering stable and accurate simulations even over very long time scales.**
diff --git a/content/news/2604SScireport.md b/content/news/2604SScireport.md
@@ -0,0 +1,14 @@
+---
+date: 2026-04-01T09:29:16+10:00
+title: "Schmidt Sciences Impact Report"
+heroHeading: ''
+heroSubHeading: 'Schmidt Sciences Impact Report'
+heroBackground: ''
+thumbnail:  'images/news/2604SScireport.png'
+images: ['images/news/2604SScireport.png']
+link: 'https://www.schmidtsciences.org/2025-report/'
+---
+
+The very first [Schmidt Sciences Impact Report](https://www.schmidtsciences.org/2025-report/) has been released, offering a snapshot of the impact made by its grantees and highlighting the importance of supporting foundational research.
+
+Among the featured stories is [M²LInES](https://www.schmidtsciences.org/profile-2025/training-the-next-generation-of-climate-models/), recognized for its work on training the next generation of climate models and advancing AI-driven Earth system science.
diff --git a/content/news/2605Perezhogin.md b/content/news/2605Perezhogin.md
@@ -0,0 +1,12 @@
+---
+date: 2026-05-01T09:29:16+10:00
+title: "Calibration of a neural network ocean closure for improved mean state and variability"
+heroHeading: ''
+heroSubHeading: 'Calibration of a neural network ocean closure for improved mean state and variability'
+heroBackground: ''
+thumbnail:  'images/news/2605Perezhogin.png'
+images: ['images/news/2605Perezhogin.png']
+link: 'https://doi.org/10.48550/arXiv.2604.06398'
+---
+
+A new [preprint](https://doi.org/10.48550/arXiv.2604.06398) led by **Pavel Perezhogin** introduces a **more systematic approach to reducing biases in coarse-resolution ocean models**, where key processes like mesoscale eddies are often unresolved. Rather than relying on ad hoc tuning, the study frames parameter adjustment as a calibration problem using **Ensemble Kalman Inversion** (EKI), applied to a neural network–based parameterization. This method significantly **improves model performance** — cutting errors in key ocean features and their variability by about half—while remaining robust to the noisy, chaotic nature of ocean dynamics. The results point to a **practical pathway for enhancing the accuracy of global ocean simulations**.
diff --git a/content/news/2605Pudig.md b/content/news/2605Pudig.md
@@ -0,0 +1,12 @@
+---
+date: 2026-05-01T09:29:16+10:00
+title: "Parameterizing Isopycnal Mixing via Kinetic Energy Backscatter in an Eddy-Permitting Ocean Model"
+heroHeading: ''
+heroSubHeading: 'Parameterizing Isopycnal Mixing via Kinetic Energy Backscatter in an Eddy-Permitting Ocean Model'
+heroBackground: ''
+thumbnail:  'images/news/2605Pudig.png'
+images: ['images/news/2605Pudig.png']
+link: 'https://doi.org/10.1029/2025MS005497'
+---
+
+This [article](https://doi.org/10.1029/2025MS005497) led by Matt Pudig explores how to better represent mesoscale turbulence in ocean models that only partially resolve eddies. The work focuses on “backscatter” parameterizations, which reintroduce energy into the system, and examines whether they can also improve how tracers mix along density surfaces. Using idealized simulations, the authors show that **backscatter alone can substantially enhance the realism of this mixing, closely matching much higher-resolution models and outperforming more conventional approaches.** The findings point to a **promising, unified framework for capturing key ocean processes and improving the fidelity of climate-scale ocean simulations** without requiring much finer resolution.
diff --git a/content/news/Newsletters/_index.md b/content/news/Newsletters/_index.md
@@ -12,6 +12,10 @@ tags:
 
 ### 2026
 
+* 05/01/2026 - [M²LInES newsletter - May 2026](https://mailchi.mp/0ea31f7e9316/m2lines-may2026)
+
+* 04/01/2026 - [M²LInES newsletter - April 2026](https://mailchi.mp/4bca7e3e26ce/m2lines-apr2026)
+
 * 03/02/2026 - [M²LInES newsletter - March 2026](https://mailchi.mp/ac4b54e185ba/m2lines-mar2026)
 
 * 02/02/2026 - [M²LInES newsletter - February 2026](https://mailchi.mp/8bf7a300bfad/m2lines-feb2026)

diff --git a/content/publications/_index.md b/content/publications/_index.md
@@ -14,14 +14,63 @@ You can also check all our publications on our **[Google Scholar profile](https:
 <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon"> M²LInES funded research
 
 ### 2026
+<div style="display: flex; align-items: center;">
+  <div style="width: 100px; height: 100px; overflow: hidden;  margin-right: 10px;">
+    <img src="/images/publications/2504-Zanna.png" style="width: 100px; height: 100px;">
+  </div>
+  <p>
+ <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
+    <strong>Moein Darman, Pedram Hassanzadeh, Laure Zanna, Ashesh Chattopadhyay</strong><br>
+    <a href="https://doi.org/10.1088/3049-4753/ae510d" target="_blank"><strong>Fourier analysis of the physics of transfer learning for data-driven subgrid-scale models of ocean turbulence</strong></a><br>
+    <i>Machine Learning Earth</i> <strong>DOI</strong>:10.1088/3049-4753/ae510d
+  </p>
+</div>
+
+<div style="display: flex; align-items: center;">
+  <div style="width: 100px; height: 100px; overflow: hidden;  margin-right: 10px;">
+    <img src="/images/publications/2504-Verma.png" style="width: 100px; height: 100px;">
+  </div>
+  <p>
+    <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
+    <strong>Tarun Verma, Feiyu Lu, Alistair Adcroft, Laure Zanna, Anand Gnanadesikan</strong><br>
+    <a href="https://doi.org/10.1029/2025MS005155" target="_blank"><strong>Deep Learning of Systematic Ocean Model Errors in a Coupled GCM from Data Assimilation Increments</strong></a><br>
+    <i>JAMES</i> <strong>DOI</strong>:10.1029/2025MS005155
+  </p>
+</div>
+
+
+<div style="display: flex; align-items: center;">
+  <div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
+    <img src="/images/publications/2603Shi.png" style="width: 100px; height: 100px;">
+  </div>
+  <p>
+   <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
+    <strong>Jia-Rui Shi, Pavel Perezhogin, Laure Zanna, Alistair Adcroft</strong><br>
+    <a href="https://doi.org/10.48550/arXiv.2603.25843" target="_blank"><strong>Impact of Data-Driven Eddy Parameterization on Climate State in an Idealized Coupled CESM Model></strong></a><br>
+    <i>Arxiv</i> <strong>DOI</strong>: 10.48550/arXiv.2603.25843
+  </p>
+</div>
+
+<div style="display: flex; align-items: center;">
+  <div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
+    <img src="/images/news/2603Kamm.png" style="width: 100px; height: 100px;">
+  </div>
+  <p>
+   <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
+    <strong>David Kamm, Julie Deshayes, Pavel Perezhogin, Etienne Meunier, Alexis Barge</strong><br>
+    <a href="https://doi.org/10.22541/essoar.177100611.18240844/v1" target="_blank"><strong>Assessing Data-Driven Eddy-Parameterizations in an Atlantic Sector Model></strong></a><br>
+    <i>ESS Open Archive</i> <strong>DOI</strong>: 10.22541/essoar.177100611.18240844/v1
+  </p>
+</div>
+
 <div style="display: flex; align-items: center;">
   <div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
     <img src="/images/news/2604-Qi.png" style="width: 100px; height: 100px;">
   </div>
   <p>
    <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
     <strong>Qi Liu, Laure Zanna, Joan Bruna</strong><br>
-    <a href="https://doi.org/10.48550/arXiv.2603.17750" target="_blank"><strong>Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems></a><br>
+    <a href="https://doi.org/10.48550/arXiv.2603.17750" target="_blank"><strong>Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems></strong></a><br>
     <i>Arxiv</i> <strong>DOI</strong>: 10.48550/arXiv.2603.17750
   </p>
 </div>
@@ -35,7 +84,7 @@ You can also check all our publications on our **[Google Scholar profile](https:
   <p>
    <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
     <strong>William Gregory, Mitchell Bushuk, James Duncan, Elynn Wu, Adam Subel, Spencer K. Clark, Bill Hurlin, Oliver Watt-Meyer, Alistair Adcroft, Chris Bretherton, Laure Zanna</strong><br>
-    <a href="https://doi.org/10.48550/arXiv.2603.12449" target="_blank"><strong>FloeNet: A mass-conserving global sea ice emulator that generalizes across climates</strong></a><br>
+    <a href="https://doi.org/10.48550/arXiv.2603.12449" target="_blank"><strong>FloeNet: A mass-conserving global sea ice emulator that generalizes across climates</strong></strong></a><br>
     <i>Arxiv</i> <strong>DOI</strong>: 10.48550/arXiv.2603.12449
   </p>
 </div>
@@ -47,7 +96,7 @@ You can also check all our publications on our **[Google Scholar profile](https:
   <p>
    <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
     <strong>Andrew Brettin, Laure Zanna</strong><br>
-    <a href="https://doi.org/10.48550/arXiv.2601.17243" target="_blank"><strong>Estimation of temperature and precipitation uncertainties using quantile neural networks</strong></a><br>
+    <a href="https://doi.org/10.48550/arXiv.2601.17243" target="_blank"><strong>Estimation of temperature and precipitation uncertainties using quantile neural networks</strong></strong></a><br>
     <i>Arxiv</i> <strong>DOI</strong>: 10.48550/arXiv.2601.17243
   </p>
 </div>
@@ -356,18 +405,6 @@ You can also check all our publications on our **[Google Scholar profile](https:
 </div>
 
 
-<div style="display: flex; align-items: center;">
-  <div style="width: 100px; height: 100px; overflow: hidden;  margin-right: 10px;">
-    <img src="/images/publications/2504-Zanna.png" style="width: 100px; height: 100px;">
-  </div>
-  <p>
- <img src="/images/newlogo.png" style="width: 1.5vw; height: 1.5hw; vertical-align: middle;" alt="DOI icon">
-    <strong>Moein Darman, Pedram Hassanzadeh, Laure Zanna, Ashesh Chattopadhyay</strong><br>
-    <a href="https://doi.org/10.48550/arXiv.2504.15487" target="_blank"><strong>Fourier analysis of the physics of transfer learning for data-driven subgrid-scale models of ocean turbulence</strong></a><br>
-    <i>Arxiv</i> <strong>DOI</strong>:10.48550/arXiv.2504.15487
-  </p>
-</div>
-
 <div style="display: flex; align-items: center;">
   <div style="width: 100px; height: 100px; overflow: hidden;  margin-right: 10px;">
     <img src="/images/news/2504-Chapman.png" style="width: 100px; height: 100px;">

diff --git a/static/images/news/2604FloeNet.gif b/static/images/news/2604FloeNet.gif
diff --git a/static/images/news/2604Liu.png b/static/images/news/2604Liu.png
diff --git a/static/images/news/2604SScireport.png b/static/images/news/2604SScireport.png
diff --git a/static/images/news/2605Perezhogin.png b/static/images/news/2605Perezhogin.png
diff --git a/static/images/news/2605Pudig.png b/static/images/news/2605Pudig.png
diff --git a/static/images/publications/2603Shi.png b/static/images/publications/2603Shi.png