Skip to content

Commit def5e19

Browse files
johannag126johannag126
authored
Merge pull request #115 from johannag126/master
add news and people
2 parents a740448 + 626cc2e commit def5e19

26 files changed

Lines changed: 152 additions & 5 deletions

‎content/news/2511Blanke.md‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
date: 2025-11-02T09:29:16+10:00
3+
title: "Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling"
4+
heroHeading: ''
5+
heroSubHeading: 'Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling'
6+
heroBackground: ''
7+
thumbnail: 'images/news/2511Blanke.png'
8+
images: ['images/news/2511Blanke.png']
9+
link: 'https://doi.org/10.48550/arXiv.2505.18017'
10+
---
11+
12+
Deep generative models, AI systems that can learn to create realistic data, are increasingly used to represent complex physical systems. However, these models often produce results that break basic physical laws, such as conservation of energy or mass. This **LEAP [study](https://doi.org/10.48550/arXiv.2505.18017)**, led by **Matthieu Blanke**, introduces a new method, called **Split Augmented Langevin (SAL)**, that ensures AI-generated outputs obey these fundamental constraints. By enforcing physical constraints in the sampling algorithm of pre-trained diffusion models, the approach makes **AI-based simulations and forecasts more accurate and reliable**. The method shows promising results in climate science applications, paving the way for AI tools that better respect the laws of nature.

‎content/news/2511Danni.md‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
date: 2025-11-02T09:29:16+10:00
3+
title: "Reducing Model Biases with ML Corrections Derived from Ocean DA Increments"
4+
heroHeading: ''
5+
heroSubHeading: 'Reducing Model Biases with Machine Learning Corrections Derived from Ocean Data Assimilation Increments'
6+
heroBackground: ''
7+
thumbnail: 'images/news/2511DanniDu.png'
8+
images: ['images/news/2511DanniDu.png']
9+
link: 'https://doi.org/10.22541/essoar.176083747.76188196/v2'
10+
---
11+
12+
Ocean models often struggle to represent how water mixes vertically, leading to persistent temperature and circulation biases. In this [preprint](https://doi.org/10.22541/essoar.176083747.76188196/v2), **Danni Du** and colleagues use machine learning (ML) to correct those biases by **learning directly from data assimilation outputs in NOAA’s GFDL SPEAR system**. When integrated into the ocean model, the ML corrections improved temperature and mixing accuracy, outperforming existing correction methods. Combining ML with traditional approaches produced even better results, leading to **more realistic sea surface temperatures and ocean structure**. This approach can be applied to other climate models, offering a powerful new way to make ocean simulations more accurate.

‎content/news/2511Samudra.md‎

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
---
2+
date: 2025-11-02T09:29:16+10:00
3+
title: "Watch: Samudra Featured on YouTube channel and in NYU News"
4+
heroHeading: ''
5+
heroSubHeading: ''
6+
heroBackground: ''
7+
thumbnail: 'images/news/Samudra.gif'
8+
images: ''
9+
link: ''
10+
---
11+
12+
M²LInES emulator Samudra was recently featured on 2 platforms:
13+
14+
🎥 **[NYU article](https://www.nyu.edu/about/news-publications/news/2025/october/accelerating-climate-modeling-at-a-lower-cost.html) and Video Feature.**
15+
16+
{{< youtube C5CQtjtU--E >}}
17+
18+
19+
<br>
20+
21+
🎬 **Prof Grace Lindsay Youtube channel** - 5 Minute Papers AI for the Planet: How AI can speed up our study of the ocean
22+
23+
{{< youtube ijyF16uy0Hk >}}
24+
</br>

‎content/news/2511Samudrace.md‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
date: 2025-11-02T09:29:16+10:00
3+
title: "New blogpost on SamudrACE"
4+
heroHeading: ''
5+
heroSubHeading: 'New blogpost on SamudrACE: the first 3D AI ocean-atmosphere-sea-ice climate emulator.'
6+
heroBackground: ''
7+
thumbnail: 'images/news/2511SamudrACE.gif'
8+
images: ['images/news/2511SamudrACE.gif']
9+
link: 'https://medium.com/@lz1955/samudrace-a-fast-accurate-efficient-3d-coupled-climate-ai-emulator-fcef3c60b079'
10+
---
11+
12+
Our latest **[blogpost](https://medium.com/@lz1955/samudrace-a-fast-accurate-efficient-3d-coupled-climate-ai-emulator-fcef3c60b079) dives into the story behind SamudrACE**, the first 3D AI ocean–atmosphere–sea-ice climate emulator. Developed in collaboration with **M²LInES, AI2, and NOAA GFDL**, SamudrACE marks a major milestone in the use of AI for climate science.
13+
14+
The post explores how the team built a model capable of simulating 1500 years of climate in just one day on a single GPU, making state-of-the-art climate modeling accessible to anyone, without the need for supercomputers or deep expertise in numerical modeling.

‎content/news/2511Sane.md‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
---
2+
date: 2025-11-02T09:29:16+10:00
3+
title: "Machine Learned Equations for Vertical Mixing in the Ocean Surface Boundary Layer"
4+
heroHeading: ''
5+
heroSubHeading: 'Machine Learned Equations for Vertical Mixing in the Ocean Surface Boundary Layer'
6+
heroBackground: ''
7+
thumbnail: 'images/news/2511Sane.png'
8+
images: ['images/news/2511Sane.png']
9+
link: 'https://doi.org/10.31219/osf.io/uab7v_v2'
10+
---
11+
12+
A new [study](https://doi.org/10.31219/osf.io/uab7v_v2), led by **Aakash Sane**, introduces **a two step method to improve how ocean surface mixing is represented in models**. First, neural networks predict vertical diffusivity while respecting key physical constraints. Then, symbolic regression converts these predictions into simple equations that match the neural network accuracy but are easier to interpret. The resulting formulas reveal how friction velocity, buoyancy flux, Earth’s rotation and boundary layer depth shape mixing and expose a flaw in the standard physics based scheme. This approach provides **a transparent, efficient and physically grounded way to model ocean vertical mixing.**

‎content/news/Newsletters/_index.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,8 +9,11 @@ tags:
99

1010

1111
Links to our past newsletters are below.
12+
1213
### 2025
1314

15+
* 11/03/2025 - [M²LInES newsletter - November 2025](https://mailchi.mp/5f5c32598bba/m2lines-nov2025)
16+
1417
* 10/01/2025 - [M²LInES newsletter - October 2025](https://mailchi.mp/0608f769fe88/m2lines-oct2025)
1518

1619
* 09/02/2025 - [M²LInES newsletter - September 2025](https://mailchi.mp/68907e6e11ec/m2lines-sep2025)

‎content/team/AmoghGulati.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
title: "Amogh Gulati"
33
draft: false
44
image: "/images/team/AmoghGulati.jpg"
5-
jobtitle: "Affiliate, Graduate Student"
5+
jobtitle: "Graduate Student"
66
promoted: true
77
weight: 25
88
Website:

‎content/team/AnurupNaskar.md‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
title: "Anurup Naskar"
3+
draft: false
4+
image: "/images/team/AnurupNaskar.png"
5+
jobtitle: "Affiliate, Graduate Student"
6+
promoted: true
7+
weight: 26
8+
Website:
9+
Position: Climate Informatics
10+
tags: [Atmosphere, Machine Learning, Climate Model Development]
11+
---
12+
13+
14+
NYU

‎content/team/DiajengWulandariAtmojo.md‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
---
2+
title: "Diajeng Wulandari Atmojo"
3+
draft: false
4+
image: "/images/team/Diajeng.jpg"
5+
jobtitle: "Affiliate, Graduate Student"
6+
promoted: true
7+
weight: 26
8+
Website:
9+
Position:
10+
tags: [Sea-Ice, Machine Learning, Climate Model Development]
11+
---
12+
13+
14+
University of Bremen

‎content/team/GoshaGeogdzhayev.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,14 @@
11
---
2-
title: "Maxime Keutgen De Greef"
2+
title: "Gosha Geogdzhayev"
33
draft: false
4-
image: "/images/team/Maxime.png"
4+
image: "/images/team/GoshaGeogdzhayev.jpeg"
55
jobtitle: "Affiliate, Graduate Student"
66
promoted: true
77
weight: 26
88
Website:
99
Position: Emulator
10-
tags: [Ocean, Machine Learning, Climate Model Development]
10+
tags: [Ocean, Atmosphere, Machine Learning]
1111
---
1212

1313

14-
Princeton University
14+
NYU

0 commit comments

Comments
 (0)