Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,13 @@ hugo new content/<name of your page>.md # create a new page
hugo server -D # serve the website on http://localhost:1313/.
```

### Page descriptions (for search results and link previews)
Add a `description:` line to the front matter of every new page:
one or two plain sentences, 120 to 155 characters, saying what the page is about.
News posts can rely on `heroSubHeading`. Team members only appear on the team
lists, so they need no description. Add `thumbnail:` to news posts so links share with an image.


### Updating Tags
Member interests are defined in the form of tags which can link to personalized landing pages.
Example for adding tag to a member and giving it a custom landing page:
Expand Down
4 changes: 3 additions & 1 deletion archetypes/default.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
---
title: "{{ replace .TranslationBaseName "-" " " | title }}"
# One or two plain sentences, 120 to 155 characters. Shown in Google results and link previews.
description: ""
date: {{ .Date }}
draft: true
---
---
10 changes: 7 additions & 3 deletions archetypes/team.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,14 @@ intro_image: images/undraw_selection_92i4.svg
intro_image_absolute: false
intro_image_hide_on_mobile: true
image: "images/team/default.png"
jobtitle: "Employee"
linkedinurl: 'https://www.linkedin.com/'
jobtitle: ""
# Optional. If left empty, a description is built from name, jobtitle and tags.
description: ""
tags: []
Website: ""
linkedinurl: 'https://www.linkedin.com/in/m2lines-project/'
draft: false
weight: 100
---

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Bibendum arcu vitae elementum curabitur vitae nunc sed. Tortor at risus viverra adipiscing at in.
M²LInES (M2LInES) is an international collaboration using interpretable machine learning to improve climate models at the air-sea-ice interface.
6 changes: 6 additions & 0 deletions config.toml
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@ enableEmoji = true
google_analytics_id=""
google_tag_manager_id = ""

[params.seo]
homeTitle = "M²LInES (M2LInES): Multiscale Machine Learning In Coupled Earth System Modeling"
description = "M²LInES (M2LInES), pronounced M-square-lines, is an international collaborative project with the goal of improving climate projections, using scientific and interpretable Machine Learning to capture unaccounted physical processes at the air-sea-ice interface."
image = "images/m2lines-share.png"
twitter = "@M2LInES"

[params.homepage]
show_call_box = true

Expand Down
1 change: 1 addition & 0 deletions content/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Home'
description: 'M²LInES or M2LInES (pronounced M-square-lines) is an international collaborative project with the goal of improving climate projections, using scientific and interpretable Machine Learning to capture unaccounted physical processes at the air-sea-ice interface.'
date: 2018-02-12T15:37:57+07:00
heroHeading: 'M²LInES - Multiscale Machine Learning In Coupled Earth System Modeling'
heroSubHeading: 'M²LInES (pronounced M-square-lines) is an international collaborative project with the goal of improving climate projections, using scientific and interpretable Machine Learning to capture unaccounted physical processes at the air-sea-ice interface.'
Expand Down
1 change: 1 addition & 0 deletions content/code/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: ' Code'
description: 'Open-source code, models and datasets from M²LInES for machine learning in climate modeling, with links to repositories and public data access.'
heroHeading: 'Code'
heroSubHeading: 'Public repository and data access'
heroBackground: '/images/photo-1542831371-29b0f74f9713.jpeg'
Expand Down
1 change: 1 addition & 0 deletions content/jobs/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Jobs'
description: 'Open positions with M²LInES in machine learning and climate modeling across all our institutions.'
heroHeading: 'Open positions'
heroSubHeading: ''
heroBackground: 'images/SouthAtlantic.A2002157.1055.250m.jpg'
Expand Down
14 changes: 14 additions & 0 deletions content/news/2610Balwada.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
---
date: 2026-10-14T09:29:16+10:00
title: "Design and Implementation of a Data-Driven Parameterization for Mesoscale Eddy-Induced Transport"
heroHeading: ''
heroSubHeading: 'Design and Implementation of a Data-Driven Parameterization for Mesoscale Eddy-Induced Transport: Idealized Two-Layer Configurations'
heroBackground: ''
thumbnail: 'images/news/2610Balwada.png'
images: ['images/news/2610Balwada.png']
link: 'https://doi.org/10.1029/2025MS005245'
---

Mesoscale eddies, the ocean’s swirling currents, move heat and tracers and drain potential energy from the large-scale circulation. Most climate models can’t fully resolve them, so their effects are approximated with the Gent-McWilliams (GM) scheme. GM captures the overall energy removal but assumes eddy fluxes always run down the gradient, missing the up-gradient and cross-gradient fluxes seen in reality. It can also dampen eddies that models partially resolve.

In new **M²LInES [work](https://doi.org/10.1029/2025MS005245) led by Dhruv Balwada**, the team developed **a machine learning parameterization free of this diffusive constraint**. Using a small, inexpensive neural network, it captures the full structure of eddy thickness fluxes while still extracting energy, adapts to both the flow and model resolution, and is tuned with a single simple parameter. **Implemented in NOAA GFDL’s MOM6 ocean model**, it performed well in idealized channel and gyre simulations at eddy-permitting and coarse resolutions.
12 changes: 12 additions & 0 deletions content/news/2610Bushuk.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
---
date: 2026-10-14T09:29:16+10:00
title: "Historical and Projected Antarctic Sea Ice Trends Across High-Resolution Coupled Model Hierarchies"
heroHeading: ''
heroSubHeading: 'Historical and Projected Antarctic Sea Ice Trends Across High-Resolution Coupled Model Hierarchies'
heroBackground: ''
thumbnail: 'images/news/2610Bushuk.jpg'
images: ['images/news/2610Bushuk.jpg']
link: 'https://doi.org/10.1029/2026GL124043'
---

Led by **Mitch Bushuk**, this **[article](https://doi.org/10.1029/2026GL124043)** investigates the hypothesis that eddy-resolving climate models may improve the simulation of Antarctic sea ice trends. Using high-resolution model hierarchies from GFDL and NCAR alongside three generations of CMIP models, the study finds **no clear relationship between ocean or atmospheric resolution and Antarctic sea ice trends**, either over the historical period or the remainder of the 21st century. Instead, models that successfully reproduce the observed trend tend to exhibit large-amplitude multidecadal variability in the Southern Ocean, suggesting that **these models may be getting the “right answer for the wrong reasons.”**
15 changes: 15 additions & 0 deletions content/news/2610ESI.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
---
date: 2026-10-14T09:29:16+10:00
title: "NYU Earth Systems Institute Launches at Climate Week NYC"
heroHeading: ''
heroSubHeading: 'NYU Earth Systems Institute Launches at Climate Week NYC'
heroBackground: ''
thumbnail: 'images/news/2610ESI.jpg'
images: ['images/news/2610ESI.jpg']
link: 'https://www.nyu.edu/about/news-publications/news/2026/october/nyu-earth-systems-institute-launches-at-climate-week-nyc.html?utm_source=nyuogst-amplify&utm_medium=email&utm_campaign=2026-10-esi-climate-week-recap&utm_content=headline-earth-systems'
---
_Left to right: Laure Zanna, Timon McPhearson, Donald Chahbazpour, Dharik Mallapragada, Miguel Modestino, V. Balaji, Sonali McDermid, Alessandra Giannini, Duncan Anderson, and Eric Vieira at the Earth Systems Institute launch. Photo Credit: Elena Olivo._

On September 21, NYU’s new **[Earth Systems Institute (ESI)](https://wp.nyu.edu/earthsys/)** made its public debut during Climate Week NYC. Launched by NYU's Office of Global Science and Technology, and **directed by Laure Zanna**, ESI brings together more than 40 scientists across Courant, Tandon, and Arts & Science to build data-driven models of the Earth system and put them in the hands of decision-makers. The afternoon featured talks on Samudra, our AI ocean emulator that can simulate 4,000 years of ocean in a single day on one GPU, the surprising greening of the Sahel, and how home electrification is reshaping peak power demand. A fellowship, a Distinguished Visitor Program, and a spring summit are planned for the year ahead.

**[Read the full story](https://www.nyu.edu/about/news-publications/news/2026/october/nyu-earth-systems-institute-launches-at-climate-week-nyc.html?utm_source=nyuogst-amplify&utm_medium=email&utm_campaign=2026-10-esi-climate-week-recap&utm_content=headline-earth-systems)**
20 changes: 20 additions & 0 deletions content/news/2610Holland.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
---
date: 2026-10-14T09:29:16+10:00
title: "Congratulations to Marika Holland, 2026 MacArthur Fellow!"
heroHeading: ''
heroSubHeading: 'Congratulations to Marika Holland, 2026 MacArthur Fellow!'
heroBackground: ''
thumbnail: 'images/news/2610Holland.jpg'
images: ['images/news/2610Holland.jpg']
link: 'https://www.macfound.org/fellows/class-of-2026/marika-holland'
---
_Photo credit: John D. and Catherine T. MacArthur Foundation._


We are thrilled to congratulate **Marika Holland**, senior scientist at NCAR’s Climate and Global Dynamics Laboratory and M²LInES PI, on being named a **2026 MacArthur Fellow**, an honor widely known as the “genius grant.”

Marika’s research explores **how polar sea ice both responds to and shapes global climate**. Her work on the ice-albedo feedback helped show how thinning ice can trigger rapid sea ice loss, and she has built these processes into the Community Earth System Model, used by researchers around the world. Her projections have even informed the listing of Emperor penguins as an endangered species.

This recognition is richly deserved. Congratulations, Marika!

Read more on the **[MacArthur Foundation website](https://www.macfound.org/fellows/class-of-2026/marika-holland)**.
3 changes: 3 additions & 0 deletions content/news/Newsletters/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Newsletters'
description: 'Past M²LInES newsletters with updates on research, people and events across the collaboration.'
heroHeading: 'Newsletters'
heroSubHeading: ''
heroBackground: '/images/andrew-dunstan-qdUDnCjo7e0-unsplash.jpeg'
Expand All @@ -11,6 +12,8 @@ tags:
Links to our past newsletters are below.

### 2026
* 10/14/2026 - [Teaching Neural Network to think like Eddies](https://mailchi.mp/462b27c260c7/m2lines-oct2026)

* 09/10/2026 - [An Ocean Emulator in your browser - September 2026](https://mailchi.mp/b280ef874950/m2lines-sep2026)

* 08/06/2026 - [AI and the Next Generation of Climate Models - August 2026](https://mailchi.mp/eafe7c4b8e1d/m2lines-aug2026)
Expand Down
1 change: 1 addition & 0 deletions content/news/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: ' News'
description: 'News from M²LInES: new papers, awards, talks, workshops and updates from our machine learning and climate modeling collaboration.'
heroHeading: 'News'
heroSubHeading: 'M²LInES in the news and news from M²LInES'
heroBackground: 'images/photo-newspapers-unsplash.jpeg'
Expand Down
1 change: 1 addition & 0 deletions content/pages/about/index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'About'
description: 'M²LInES reimagines climate model development with scientific machine learning, learning physics from data to make climate projections more reliable.'
date: 2018-12-06T09:29:16+10:00
layout: 'about'
heroHeading: 'About Us'
Expand Down
1 change: 1 addition & 0 deletions content/pages/code-of-conduct/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Code of conduct'
description: 'In this page we share our code of conduct, the rules and guidelines that shape our conduct and interactions with others within the M2LInES team'
date: 2018-12-06T09:29:16+10:00
heroHeading: 'Code of Conduct'
heroSubHeading: ""
Expand Down
74 changes: 74 additions & 0 deletions content/publications/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Publications'
description: 'Papers and preprints from M²LInES or related to M²LInES topics on machine learning parameterizations, climate emulators, and data-driven ocean, atmosphere and sea-ice physics.'
heroHeading: 'Publications'
heroSubHeading: 'Research work and relevant papers by our team'
heroBackground: 'images/susan-q-yin-2JIvboGLeho-unsplash.jpg'
Expand All @@ -15,6 +16,54 @@ You can also check all our publications on our **[Google Scholar profile](https:

### 2026

<div class="publication">
<div class="publication-image">
<img src="/images/publications/2610Levine.png">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Xavier J Levine, Griffin Mooers, Jack W Atkinson, Marat F Khairoutdinov, Janni Yuval, Dominic Orchard, Paul A O'Gorman</strong><br>
<a href="https://doi.org/10.48550/arXiv.2610.20405" target="_blank"><strong>Improved Precipitation Variability in the Community Atmosphere Model through Implementation of a Neural-Network Deep Convection Scheme</strong></a><br>
<i>ArXiv</i> <strong>DOI</strong>: 10.48550/arXiv.2610.20405
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/publications/2026Balwada.png">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Georgy E Manucharyan, Scott A Martin, Dhruv Balwada, Jinbo Wang</strong><br>
<a href="https://doi.org/10.1146/annurev-marine-040324-023244" target="_blank"><strong>Deep Learning to Infer Ocean Dynamics</strong></a><br>
<i>Annual Review of Marine Science</i> <strong>DOI</strong>: 10.1146/annurev-marine-040324-023244
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/news/2610Balwada.png">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Dhruv Balwada, Pavel Perezhogin, Alistair Adcroft, Laure Zanna</strong><br>
<a href="https://doi.org/10.1029/2025MS005245" target="_blank"><strong>Design and implementation of a data‐driven parameterization for mesoscale eddy‐induced transport: Idealized two‐layer configurations</strong></a><br>
<i>JAMES</i> <strong>DOI</strong>: 10.1029/2025MS005245
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/publications/2026Atmojo.png">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Diajeng W Atmojo, Katja Weigel, Arthur Grundner, Marika M Holland, Dmitry Sidorenko, Veronika Eyring</strong><br>
<a href="https://doi.org/10.5194/tc-20-4437-2026" target="_blank"><strong>Data-driven equation discovery of a sea ice albedo parametrisation</strong></a><br>
<i>The Cryosphere</i> <strong>DOI</strong>: 10.5194/tc-20-4437-2026
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/news/2604-FloeNet.png">
Expand All @@ -27,6 +76,31 @@ You can also check all our publications on our **[Google Scholar profile](https:
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/publications/2026Perezhogin.jpg">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Pavel Perezhogin, Alistair Adcroft, Laure Zanna</strong><br>
<a href="https://doi.org/10.1029/2026GL123513" target="_blank"><strong>Calibration of a neural network ocean closure for improved mean state and variability</strong></a><br>
<i>GRL</i> <strong>DOI</strong>: 10.1029/2026GL123513
</p>
</div>

<div class="publication">
<div class="publication-image">
<img src="/images/publications/2026SubelZanna.png">
</div>
<p class="publication-text">
<img src="/images/newlogo.png" class="doi-icon" alt="DOI icon">
<strong>Adam Subel, Laure Zanna</strong><br>
<a href="https://doi.org/10.48550/arXiv.2608.13494" target="_blank">
<strong>Paleoclimate Boundary Conditions as an Out-of-Sample Test for the Forced Response of Ocean Climate Emulators</strong>
</a><br>
<i>Arxiv</i> <strong>DOI</strong>:10.48550/arXiv.2608.13494
</p>
</div>

<div class="publication">
<div class="publication-image">
Expand Down
1 change: 1 addition & 0 deletions content/publications/archive/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Publications Archive'
description: 'Earlier M²LInES publications on machine learning for climate modeling, including subgrid parameterizations for the ocean, atmosphere and sea ice.'
heroHeading: 'Publications Archive'
heroSubHeading: ''
heroBackground: 'images/susan-q-yin-2JIvboGLeho-unsplash.jpg'
Expand Down
3 changes: 2 additions & 1 deletion content/research/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: ''
title: 'Research themes'
description: 'Machine learning parameterizations for ocean, atmosphere and sea ice, climate model emulators, and data-driven discovery in climate physics.'
heroHeading: 'Research themes'
heroSubHeading: ''
heroBackground: '/images/32109555763_eb9bb215ef_k.jpg'
Expand Down
78 changes: 78 additions & 0 deletions content/research/talks/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Talks'
description: 'Recorded talks by M²LInES researchers on machine learning for climate modeling, parameterization and emulation.'
heroHeading: 'Talks'
heroSubHeading: ''
heroBackground: '/images/headway-F2KRf_QfCqw-unsplash.jpeg'
Expand Down Expand Up @@ -121,6 +122,83 @@ p {
<h1 style="font-family: Helvetica, serif; text-align: center;">Recent talks</h1>
<hr style="width: 100%; margin-top: 20px; border-color: #333;">

## *2025*
<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
<div onclick="window.open('https://www.youtube.com/watch?v=DU88-ov2vXs&t=2730s');">
<a href="#" class="fill-div">
<img src="https://img.youtube.com/vi/DU88-ov2vXs/0.jpg" alt="Video Preview">
</a>
</div>
</div>
<p>
<strong>Will Gregory</strong><br>
<em>How is AI shaping Arctic climate modeling and observational research?</em><br>
IARPC Webinar - August &#128187; &#127758;
</p>
</div>

<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
<div onclick="window.open('https://www.youtube.com/watch?v=eWSWdj_7pB4');">
<a href="#" class="fill-div">
<img src="https://img.youtube.com/vi/eWSWdj_7pB4/0.jpg" alt="Video Preview">
</a>
</div>
</div>
<p>
<strong>Will Chapman</strong><br>
<em>Improving climate model bias and variability via a Convolutional Neural Network (CNN)-based state-dependent model-error correction</em><br>
NCAR Mesoscale and Microscale Meteorology Invited Seminar - May &#128187; &#127758;
</p>
</div>

<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
<div onclick="window.open('https://youtu.be/9xr2WBzzbPs');">
<a href="#" class="fill-div">
<img src="https://img.youtube.com/vi/9xr2WBzzbPs/0.jpg" alt="Video Preview">
</a>
</div>
</div>
<p>
<strong>Laure Zanna</strong><br>
<em>Reshaping climate modeling with AI</em><br>
Collège de France - AI and Mathematics for Meteorology and Climatology - May &#128187; &#127878; &#127758;
</p>
</div>

<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
<div onclick="window.open('https://www.birs.ca/events/2025/5-day-workshops/25w5380/videos/watch/202505270857-Du.html');">
<a href="#" class="fill-div">
<img src="/images/newlogo.png" alt="Video Preview">
</a>
</div>
</div>
<p>
<strong>Danni Du</strong><br>
<em>Improved MJO prediction across the Maritime Continent with sea surface salinity assimilation</em><br>
BIRS MJO Predictability Workshop - May &#128202; &#127758;
</p>
</div>

<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
<div onclick="window.open('https://vimeo.com/1073527258/5aeceea455');">
<a href="#" class="fill-div">
<img src="/images/newlogo.png" alt="Video Preview">
</a>
</div>
</div>
<p>
<strong>Alistair Adcroft</strong><br>
<em>Ocean Heat Uptake in the Era of Eddying Ocean Models and AI</em><br>
ECMWF 50th Anniversary and Annual Seminar - March &#128187; &#127758;
</p>
</div>


## *2024*
<div style="display: flex; align-items: center;">
<div style="width: 100px; height: 100px; overflow: hidden; margin-right: 10px;">
Expand Down
1 change: 1 addition & 0 deletions content/research/talks/archive/_index.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
title: 'Archive Talks'
description: 'Earlier recorded talks by M²LInES researchers on machine learning for climate modeling, parameterization and emulation.'
heroHeading: 'Archive Talks'
heroSubHeading: ''
heroBackground: '/images/headway-F2KRf_QfCqw-unsplash.jpeg'
Expand Down
Loading
Loading