diff --git a/content/news/2602Nasser.md b/content/news/2602Nasser2.md
similarity index 100%
rename from content/news/2602Nasser.md
rename to content/news/2602Nasser2.md
diff --git a/content/news/2603Falasca.md b/content/news/2603Falasca.md
new file mode 100644
index 00000000..ea082cd5
--- /dev/null
+++ b/content/news/2603Falasca.md
@@ -0,0 +1,12 @@
+---
+date: 2026-03-02T09:29:16+10:00
+title: "Causally constrained reduced-order neural models of complex turbulent dynamical systems"
+heroHeading: ''
+heroSubHeading: 'Causally constrained reduced-order neural models of complex turbulent dynamical systems'
+heroBackground: ''
+thumbnail:  'images/news/2603Falasca.png'
+images: ['images/news/2603Falasca.png']
+link: 'https://doi.org/10.22541/essoar.177100611.18240844/v1'
+---
+
+In this [work](https://doi.org/10.48550/arXiv.2602.13847), **Fabrizio Falasca** and **Laure Zanna** introduce a **flexible framework that combines response theory and score matching to eliminate spurious, noncausal dependencies in reduced-order neural emulators of turbulent systems.** Using the stochastic **Charney–DeVore model** as a proof of concept for low-frequency atmospheric variability, they demonstrate that **enforcing causal constraints significantly improves emulator responses** to both weak and strong external forcings, even when trained solely on unforced data. The framework is broadly applicable to complex turbulent systems and can be seamlessly integrated into standard neural network architectures, offering a principled **path toward more reliable climate emulators**.
\ No newline at end of file
diff --git a/content/news/2603Kamm.md b/content/news/2603Kamm.md
new file mode 100644
index 00000000..7c905b0b
--- /dev/null
+++ b/content/news/2603Kamm.md
@@ -0,0 +1,12 @@
+---
+date: 2026-03-02T09:29:16+10:00
+title: "Assessing Data-Driven Eddy-Parameterizations in an Atlantic Sector Model"
+heroHeading: ''
+heroSubHeading: 'Assessing Data-Driven Eddy-Parameterizations in an Atlantic Sector Model'
+heroBackground: ''
+thumbnail:  'images/news/2603Kamm.png'
+images: ['images/news/2603Kamm.png']
+link: 'https://doi.org/10.22541/essoar.177100611.18240844/v1'
+---
+
+Mesoscale eddies are the ocean’s primary reservoir of kinetic energy, yet most climate models cannot fully resolve them due to computational limits. In this [study](https://doi.org/10.22541/essoar.177100611.18240844/v1) led by **David Kamm**, two **machine-learning–based eddy parameterizations**, Zanna and Bolton (2020) parameterization (ZB20) and Guillaumin and Zanna (2021) parameterization (GZ21), are **implemented in the NEMO ocean model and evaluated against high-resolution simulations.** While GZ21 shows systematic biases linked to grid spacing and does not improve coarse-resolution performance, **ZB20 successfully captures subgrid energy transfers, leading to improved kinetic energy spectra and large-scale circulation.** The results highlight that carefully designed, resolution-aware training data are essential for developing robust and generalizable data-driven eddy parameterizations.
\ No newline at end of file
diff --git a/content/news/Newsletters/_index.md b/content/news/Newsletters/_index.md
index 4b7516ee..95d47354 100644
--- a/content/news/Newsletters/_index.md
+++ b/content/news/Newsletters/_index.md
@@ -12,6 +12,8 @@ tags:
  
 ### 2026
 
+* 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)
 
 * 01/05/2026 - [M²LInES newsletter - January 2026](https://mailchi.mp/be4f07420e28/m2lines-jan2026)
diff --git a/content/publications/_index.md b/content/publications/_index.md
index 727cc372..c2a990de 100644
--- a/content/publications/_index.md
+++ b/content/publications/_index.md
@@ -14,6 +14,20 @@ 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/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>
+    <i>Arxiv</i> <strong>DOI</strong>: 10.48550/arXiv.2603.17750
+  </p>
+</div>
+
+
+
 <div style="display: flex; align-items: center;">
   <div style="width: 200px; height: 100px; overflow: hidden; margin-right: -30px;">
     <img src="/images/news/2604-FloeNet.png" style="width: 100px; height: 100px;">
diff --git a/static/images/news/2603Falasca.png b/static/images/news/2603Falasca.png
new file mode 100644
index 00000000..59198fe2
Binary files /dev/null and b/static/images/news/2603Falasca.png differ
diff --git a/static/images/news/2603Kamm.png b/static/images/news/2603Kamm.png
new file mode 100644
index 00000000..17b49455
Binary files /dev/null and b/static/images/news/2603Kamm.png differ
diff --git a/static/images/news/2604-Qi.png b/static/images/news/2604-Qi.png
new file mode 100644
index 00000000..9deb6bf0
Binary files /dev/null and b/static/images/news/2604-Qi.png differ