Blanka Balogh
banner
blankabalogh.bsky.social
Blanka Balogh
@blankabalogh.bsky.social
Climate modeling & AI researcher @ Meteo-France/CNRM.
When I’m not coding, I’m probably out running!
📍Toulouse, France
Back here after a while. I had a wonderful beginning of the week in Zurich at the Exclaim! Symposium where I had a poster.
It really was amazing, the quality of the talks was GREAT and the people amazing! Many thanks and kudos to the organizers!
June 4, 2025 at 8:05 PM
As 2024 comes to an end, here are my 3 favorite papers of the year on NN-based weather prediction. I’ve chosen ones that might not be on your radar but stand out for their originality or insights.
December 29, 2024 at 7:48 AM
Reposted by Blanka Balogh
With < 48 hours to go, ECMWF gets to claim this year's Christmas-time AI weather forecasting mic drop: arxiv.org/abs/2412.15687
GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations
We introduce GraphDOP, a new data-driven, end-to-end forecast system developed at the European Centre for Medium-Range Weather Forecasts (ECMWF) that is trained and initialised exclusively from Earth ...
arxiv.org
December 23, 2024 at 4:31 PM
Hi Bluesky! I realize I’ve never introduced myself. I’m a research scientist in the climate research group at Météo-France, where I focus on developing a hybrid global climate model that combines AI and physics based modeling.
1/3
December 23, 2024 at 5:47 PM
Reposted by Blanka Balogh
If you're training models with more than one loss term, I can again strongly recommend our ConFIG optimizer: tum-pbs.github.io/ConFIG/ , simply swap out Adam&Co. for ConFIG, and you can potentially see substantial reductions in your training loss 😁 We'd also be curious to hear how it works for you
December 10, 2024 at 7:11 AM
Reposted by Blanka Balogh
The new ACE2 climate emulator from Oliver Watt-Meyer et al has very compelling results, with results that look comparable to NeuralGCM. Congrats to the AI2 team!
arxiv.org/abs/2411.112...
ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses
Existing machine learning models of weather variability are not formulated to enable assessment of their response to varying external boundary conditions such as sea surface temperature and greenhouse...
arxiv.org
November 21, 2024 at 6:47 PM
Here’s a starter pack for AI in Weather & Climate research! 🎉 I hope to see this grow over time. If I missed anyone, please let me know!

go.bsky.app/D6uzmRv
November 18, 2024 at 7:20 AM
Back from ECMWF !
November 17, 2024 at 7:10 AM
On recrute ! Nous recherchons un ingénieur de recherche en IA appliqué à la prévision numérique du temps, au CNRM.

CDD de 21 mois à partir du 01/04/2024, à Toulouse. Date limite de candidature : 05/01/2024.
emploi.cnrs.fr/Offres/CDD/U...
December 18, 2023 at 7:45 AM
Hi, I am Blanka, and I am a research scientist using AI to make climate models more accurate. I enjoy discussing the use of AI in weather forecasting and climate, especially in atmospheric modeling.
December 10, 2023 at 7:36 AM