Nikolay Koldunov's Avatar

Nikolay Koldunov

@oceanographer

Oceanographer, climate and ocean modeler, interested in ML for climate and LLMs. Senior scientist at AWI. Working on FESOM2 unstructured ocean model, km-scale climate modelling, data visualisation. More info: https://koldunovn.github.io/

767
Followers
897
Following
84
Posts
21.11.2024
Joined
Posts Following

Latest posts by Nikolay Koldunov @oceanographer

Public Lecture: New Perspectives on Climate Change from km-scale Earth System Models The EERIE Project aims to expand our understanding of the role of ocean eddies – an integral part of the ocean’s weather – in the Earth’s climate system in a warming world. In order to achieve this, w...

🔴 Are you in #Barcelona? Are you interested in #ClimateChange?

Then this **EERIE Project public lecture** is for you! ⤵️

💡 New Views of Climate Change - Insights from Kilometer-Scale Earth System Models

🗓️ Monday, March 9
🕕 6pm CET
🏢 @bsc-cns.bsky.social

Register here: events.hifis.net/event/3767/

06.03.2026 10:42 👍 6 🔁 3 💬 0 📌 0
Post image Post image Post image

We posted a preprint on arXiv about PANGAEA-GPT, a multi-agent system for autonomous data discovery and analysis in geoscientific archives. Plots below are generated by the system, and you can read about the steps system made in the paper. 🧪

📄 arxiv.org/abs/2602.21351
💻 github.com/CliDyn/panga...

27.02.2026 10:33 👍 4 🔁 1 💬 0 📌 0
Video thumbnail

Built a demo agent for ERA5 on @earthmover.io Arraylake: fast slice access means you can retrieve, iterate & visualize without the coffee breaks. Eurus supports NL→retrieval+analysis, CLI/web/MCP, and a Python REPL (pandas/xarray/cartopy). Video below. Repo+HF: lnkd.in/deQMCNmH lnkd.in/dAbhnKSr

26.02.2026 07:56 👍 5 🔁 1 💬 0 📌 0
Video thumbnail

🌍 ClimSight is a system that allows users to get answers to climate-related questions based on very local climate information. Check out the short video to learn the core ideas, and dive into the paper if you’d like to explore the details:

📄 lnkd.in/eReWQ4x6 🧪

28.10.2025 11:57 👍 6 🔁 2 💬 0 📌 0
Mean July 2-m air temperature (1991-2020). (a) ERA5 reanalysis. (b) LLM GPT-5 predictions. Both panels are shown on a 1° grid.

Mean July 2-m air temperature (1991-2020). (a) ERA5 reanalysis. (b) LLM GPT-5 predictions. Both panels are shown on a 1° grid.

How much do LLMs “know” about present-day climate?
We asked 17 models for July 1991–2020 temperatures at 15 000+ land points — and many did surprisingly well!
Preprint: arxiv.org/abs/2510.08043 🧪
#LLM #Climate

10.10.2025 07:02 👍 13 🔁 4 💬 0 📌 0
hk25-teams/hk25-DestinE at main · digital-earths-global-hackathon/hk25-teams Analysis scripts for the global hackathon. Contribute to digital-earths-global-hackathon/hk25-teams development by creating an account on GitHub.

Access is currently restricted to EU institutes. You can follow instructions and examples here to access the data: github.com/digital-eart...

23.06.2025 20:20 👍 1 🔁 0 💬 0 📌 0
From Past to Future - The Central European Floods, 2024 in a Changing Climate.” – Storm Boris
From Past to Future - The Central European Floods, 2024 in a Changing Climate.” – Storm Boris YouTube video by ECMWF

DestinE’s just dropped “From Past to Future” videos: km-scale replays of real floods & hurricanes under past, present & +2 °C climates. See exactly how warming reshapes impacts—turning high-res science into must-see visuals. 🧪

destine.ecmwf.int/news/storyli...

www.youtube.com/watch?v=5V62...

23.06.2025 10:52 👍 6 🔁 1 💬 1 📌 0

New opportunity in our group!

04.04.2025 08:21 👍 1 🔁 0 💬 0 📌 0
Preview
Accelerating Earth Science Discovery via Multi-Agent LLM Systems This Perspective explores the transformative potential of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) in the geosciences. Users of geoscientific data repositories face challenges...

How will interaction with geophysical data evolve in the age of AI? 🤖🌍

In our latest preprint, we explore this question - not just conceptually, but with a hands-on prototype using the PANGAEA archive. Check it out!

arxiv.org/abs/2503.05854

11.03.2025 08:32 👍 6 🔁 3 💬 0 📌 0
Video thumbnail

🚨 Last chance to submit your application! 🚨

🌊 Scientist in High-Resolution Sea Ice Modeling
🔗 jobs.awi.de/Vacancies/19...

🧠 Scientist in AI-based Emulation for High-Resolution Sea Ice Modeling
🔗 jobs.awi.de/Vacancies/19...

Please share! 🧪❄️🌍 #ScienceJobs #SeaIce #AI

27.02.2025 07:36 👍 9 🔁 7 💬 0 📌 0

Wow! :)

26.02.2025 17:42 👍 1 🔁 0 💬 1 📌 0
Background of world map with grid overlaid. Text: "AIFS operational"

Background of world map with grid overlaid. Text: "AIFS operational"

We have taken our Artificial Intelligence Forecasting System (AIFS) into operations today to run side by side with our physics-based weather forecasts. The #AIFS outperforms traditional models for many measures, at a fraction of energy use. ➡️ www.ecmwf.int/en/about/med...
#AI #MachineLearning

25.02.2025 11:07 👍 145 🔁 63 💬 3 📌 15

What is the resolution? :)

26.02.2025 09:46 👍 1 🔁 0 💬 1 📌 0

One of the greatest things we do in #DestinE is high-resolution storylines, which show how present-day extreme events might unfold in the future. Check out this ECMWF blog post for details on how it’s done! 🧪

24.02.2025 11:56 👍 4 🔁 0 💬 0 📌 0

Alfred Wegener institute is finally here @awiexpedition.bsky.social !!!

19.02.2025 20:48 👍 6 🔁 0 💬 0 📌 0
This image is a global visualization of aerosol distributions on September 5, 2020, at 00:00 UTC. It represents different types of aerosols using a color-coded scheme:
	•	Red represents dust (du), primarily visible over arid regions like the Sahara Desert and extending into the Atlantic.
	•	Blue indicates sea salt (ss), prominent over the oceans, particularly in stormy regions.
	•	Green signifies carbonaceous aerosol (ca), which is associated with biomass burning and pollution, visible over regions like the Amazon, Central Africa, and parts of Southeast Asia.
	•	Yellow shows sulfuric aerosol (su), often linked to volcanic emissions and industrial activity.

The image is overlaid on a world map with latitude and longitude markers. The transparency of the colors varies to indicate concentration levels, with fully transparent areas representing minimal aerosol presence and fully opaque areas representing maximum concentrations. The right-hand legend provides a scale for interpreting the aerosol concentrations in milligrams per square meter.

This image is a global visualization of aerosol distributions on September 5, 2020, at 00:00 UTC. It represents different types of aerosols using a color-coded scheme: • Red represents dust (du), primarily visible over arid regions like the Sahara Desert and extending into the Atlantic. • Blue indicates sea salt (ss), prominent over the oceans, particularly in stormy regions. • Green signifies carbonaceous aerosol (ca), which is associated with biomass burning and pollution, visible over regions like the Amazon, Central Africa, and parts of Southeast Asia. • Yellow shows sulfuric aerosol (su), often linked to volcanic emissions and industrial activity. The image is overlaid on a world map with latitude and longitude markers. The transparency of the colors varies to indicate concentration levels, with fully transparent areas representing minimal aerosol presence and fully opaque areas representing maximum concentrations. The right-hand legend provides a scale for interpreting the aerosol concentrations in milligrams per square meter.

Preprint summarizing the first results from the nextGEMS project, which prepares several coupled models to run at kilometer scale: egusphere.copernicus.org/preprints/20... 🧪

19.02.2025 10:48 👍 12 🔁 4 💬 0 📌 0

@carbonbrief.org lists our December paper among the most featured 2024 papers, current score 2,644 - top of the charts for @altmetric.com mentions on @bsky.app 🤯

📈 www.carbonbrief.org/analysis-the...

🔓A free-access reprint link to our paper can be found on Helges website www.awi.de/en/about-us/...

11.02.2025 10:42 👍 14 🔁 4 💬 0 📌 1
Post image Post image

My wife just won the Bremen Women's Chess Championship 2025 and qualified for the German National Championship! Next stop: Munich! So proud of her!

09.02.2025 16:42 👍 9 🔁 0 💬 0 📌 0

Yes this time is very warm and practically without snow. But I was happy to see at least some sea ice from the fairy to Suomenlinna :)

07.02.2025 22:11 👍 0 🔁 0 💬 0 📌 0
Post image

It's always great to visit Helsinki-one of my favorite cities in the world. This time, I caught a glimpse of sea ice, which we’ll be modeling in the @terradt.bsky.social project (by the way, we're hiring!). The project kicked off in Helsinki this week.

07.02.2025 19:37 👍 9 🔁 1 💬 1 📌 0
Video thumbnail

🚨 Job Alert! 🚨

Our team is hiring for the @terradt.bsky.social project.

🌊 Scientist in High-Resolution Sea Ice Modeling
🔗 jobs.awi.de/Vacancies/19...

🧠 Scientist in AI-based Emulation for High-Resolution Sea Ice Modeling
🔗 jobs.awi.de/Vacancies/19...

Please share! 🧪❄️🌍 #ScienceJobs #SeaIce #AI

04.02.2025 09:50 👍 16 🔁 6 💬 1 📌 0

This is the description of our km-scale coupled climate model configuration. A lot of details in a thread from @trackow.bsky.social 🧪

13.01.2025 09:00 👍 17 🔁 3 💬 0 📌 0
Post image

New IBCAO (International Bathymetric Chart of the Arctic Ocean) version is out: doi.org/10.1038/s415...

Many of us who study the Arctic now need to update our Arctic Bathymetry posters on our walls! :)

Figure below shows a comparison of versions 4 and 5. 🧪🌊

10.01.2025 13:38 👍 13 🔁 4 💬 0 📌 0

Great thread from @jhauck.bsky.social with more details on this study 🧪

06.01.2025 23:18 👍 19 🔁 2 💬 0 📌 0

🧪

06.01.2025 19:47 👍 9 🔁 0 💬 0 📌 0
Post image

Increased sunlight and more nutrients in the Arctic Ocean won’t boost carbon storage as expected :(
🌊🧪 #FESOM

Article in Nature Climate Change: www.nature.com/articles/s41...

Press release from AWI: www.awi.de/en/about-us/...

06.01.2025 15:00 👍 12 🔁 4 💬 1 📌 0

My book is still out there! Please use, adapt, and help maintain if you find it helpful for teaching!

14.12.2024 19:49 👍 173 🔁 47 💬 5 📌 0
Post image Post image Post image

Goodbye Washington, it was fun! #AGU24

14.12.2024 14:21 👍 8 🔁 0 💬 1 📌 0
Leveraging Machine Learning algorithms for improved Arctic sea-ice prediction using the Met Office suite of models | UCL Trees This project leverages advanced satellite remote sensing and machine learning (ML) to improve Arctic sea-ice forecasting. Traditional sea-ice models often develop significant biases in summer, particu...

Join me and the polar team here in UCL Earth Sciences + Met Office on an exciting CASE studentship looking at Leveraging Machine Learning algorithms for improved Arctic sea-ice prediction using the Met Office suite of models ❄️ + 💻 +🛰️

www.trees-dla.ac.uk/projects/lev...

13.12.2024 19:33 👍 3 🔁 2 💬 2 📌 0
Session OS1.1

Exploring the Arctic Ocean? Planning to attend EGU25?

Submit an abstract to our session:"Changes in the Arctic Ocean, Sea Ice, and Subarctic Sea Systems: Observations, Models, and Perspectives" (t.ly/BvM9l)

Spread the word, and you see in Vienna for exciting talks, posters and discussions!

10.12.2024 14:32 👍 5 🔁 8 💬 0 📌 1