New article: Earth System Data Cubes: Avenues for advancing Earth system research 👉 bit.ly/40CAVAP David Montero Loaiza, Miguel Mahecha, Guido Kraemer, Anca Anghelea, Felix Cremer, Chaonan Ji, Teja Kattenborn, Laura Martínez Ferrer, Francesco Martinuzzi, Maximilian Söchting, khalil teber #AI #datacubes

According to an article by our project coordinator Markus Donat (BSC-CNS), alongside other researchers, in nature: 👉 By the end of the century, the longest dry spells in some areas could last 10 days longer than previously expected. Learn more: nature.com/articles/s4158…

💡 New Preprint! What are the benefits of an online versus offline learning approach? Explore our application of online training approach to learning subgrid parameterisations of baroclinic ocean #eddies. 👉 Find out more: arxiv.org/abs/2411.14106 #ESMs #ClimateScience

🚀 Registration Now Open for the ELLIS Summer School: AI for Earth & Climate Sciences! 🌍🤖 Join us in Jena, Germany from September 1–5, 2025 📅 Apply now through March 31. Notifications: End of April. 🔗 ellis-jena.eu/summer-school-… 🎯 @unijena, Max Planck Institute for Biogeochemistry, Carl-Zeiss-Stiftung

💡 New Paper! Check out how to better represent the formation of thin low-level clouds in atmospheric models! Our #MachineLearning model enhances vertical detail in temperature and humidity profiles to improve cloud fraction. 👉 Learn more: rmets.onlinelibrary.wiley.com/doi/10.1002/as…

💡 New Paper! Have you ever wondered, in which ways #ArtificialIntelligence can help us to better predict and respond to #ExtremeEvents? 👉Find out what #AI can already do, its challenges and opportunities: nature.com/articles/s4146…

What are the climate models we are working on? Let’s start with the land models: LPJ-GUESS (Lund University): a process-based dynamic vegetation-terrestrial ecosystem model where we focus on forest dynamics. 👉 Learn more: web.nateko.lu.se/lpj-guess/ #ClimateResearch

💡 New Paper! #MachineLearning improves #EarthSystemModels, but explaining its added value is tough. We propose using Pareto-optimal models to distill ML's added value representing cloud cover, radiative transfer and tropical precipitation. 👉 Check out: arxiv.org/abs/2408.02161#

💡 New Preprint! How to improve plant physiological processes in #ESM? Check out our HYBRID-JSBACH4 model using feed-forward neural networks pre-trained on observations capturing variability in stomatal conductance while reducing transpiration bias! 👉 essopenarchive.org/doi/full/10.22…

🌍 AI is transforming climate research! Catch us at #EGU25 presenting cutting-edge work on applying #MachineLearning, hybrid models, and causal discovery in climate research. ⚡️ Don’t miss: Camps-Valls, Reid, Ouala, Beucler + more! #AI4Climate #ML4Science #EGU25 #ClimateAI

🔥 Heatwaves, flash floods & weird weather? We’re digging into climate extremes at #EGU25 and how these events link to climate change. ⚡️ Catch talks by Schumacher, Ivanov, Seeber, and more! #ExtremeClimate #WeatherEvents #EGU25 #ClimateScience

🌱 What’s up with carbon sinks, wildfires & ecosystem feedbacks in a changing climate? We’ve got you at #EGU25. Models, remote sensing & field data combined. Talks by Ilyina, Behncke, Nieradzik, Gomarasca & co. 🌍 #CarbonScience #ClimateFeedbacks #EGU25

AI4PEX @ #EGU25 We started the week in Vienna with talks on heatwaves, wildfires and extreme evaporation by D. Schumacher, L. Nieradzki & Y. Markonis. On Day 2 we dived deeper into ocean modeling with H. Li and model evaluation using the ESMValTool by V. Predoi. #CINEA #ESM

#AI4PEX & #EXPECT joining forces to improve prediction of Climate Extremes 🤝Fantastic momentum at #EGU25! Teams from two #HorizonEU projects came together to explore synergies and plan future collaboration. 🚀What’s next? We're aiming for a joint hackathon and an ECR meeting.

💡 New Paper! Clouds are crucial for climate modeling, affecting sunshine, heat, and rainfall. Traditional models are coarse, new methods involve high-detail simulations and #MachineLearning to predict cloud cover to improve #HybridModels. 👉 Learn more: agupubs.onlinelibrary.wiley.com/doi/full/10.10…

Today we are kicking off the 1st #AI4PEX General Assembly in Lund, Sweden. Today, we started with a workshop on Doing Interdisciplinarity to set the stage for an effective communication across disciplinary boundaries, moderated by @CatrinFinkenauer from Utrecht University.

#AI4PEX GA Day 2: in-depth scientific talks and posters on our main achievements so far, followed by a discussion on next steps for the atmosphere, ocean and land teams. In the evening we went to Kulturen Open Air Museum, immersing in the history of the region #CINEA #HorizonEU

AI4PEX GA Day 3 we are mainly focusing on the methodological aspects: How to improve benchmarking? What can explainable AI do to improve our parametrizations? Highlight was the keynote by Dave Lawrence (UCAR) on how #ArtificialIntelligence is entering the #ESMs development.

Last day of our #AI4PEX GA is again reserved for workshops. Moderated by Fangfei Lan from UNIL we spend the morning focusing on Neural Operator Learning. In the afternoon, we build our own hybrid model using the SINDBAD modeling framework, led by Nuno Carvalhais from @MPG_BGC.

🚀 Excited to share our team’s contributions at the ESA Living Planet Symposium next week in Vienna! Catch us across multiple sessions on carbon fluxes, EO data consistency, AI for climate science & more. #LPS25 🌍🛰️ #EarthObservation #EarthSystemModeling