🌍 Registration OPEN: ELLIS Winter School on AI & ML for Earth System Science! 📍 Jena, Germany 🗓️ 1.-5. March 2027 Organized by AI4PEX, ELIAS & ELLIS Unit Jena + top EU partners. ⏰ Deadline: 15 Nov 2026 (23:00 CET) 🔗 Find our more: ai4pex.org/Training/School20…

💡New paper! Can satellites reveal how forests are disturbed? A new ML framework infers disturbance rate, severity, gap size & mortality from biomass patterns—producing the first globally continuous, observation-constrained disturbance regime dataset. 👉 doi.org/10.5194/essd-18-5895…

💡Weather or climate? Why choose? A new paper explores how AI could help bridge weather prediction & climate projection within unified frameworks—while highlighting challenges around trust, fairness, transparency, energy use & global inequality. 👉doi.org/10.1038/s41467-026-7…

🌟 Celebrating our AI4PEX postdocs during #PostdocAppreciationWeek! 🌍🤖 From AI-powered Earth observation to climate extremes, hybrid modelling and uncertainty, they are advancing our understanding of a changing planet. 👏 Thank you for your curiosity and creativity!

💡 How does vegetation affect soil moisture far downwind? Using atmospheric transport + deep learning, we find upwind information provides 67% of predictive power, with vegetation explaining 15%. Effects vary strongly across humid & semi-arid regions. 👉doi.org/10.1038/s41467-026-7…

💡 New paper! Summer heat extremes are changing—not just becoming hotter, but lasting longer. By comparing 1-in-100-year summers in today's and preindustrial climates, we show that faster soil drying makes prolonged heatwaves more likely. 👉 doi.org/10.1029/2026EF008241

As #ClimateChange hits harder every year, droughts and water scarcity are becoming more severe. During #WorldWaterWeek, we’re reminded that water links atmosphere, land and ocean, and understanding these links is key to predict droughts and support sustainable water management.

💡 New Paper! How are European winter extremes linked to atmospheric circulation? Using the co-recurrence ratio (α), we find coupling depends strongly on the circulation domain and height, but little on the extreme threshold we define. 👉 Learn more: doi.org/10.1007/s00382-025-0…

💡 New preprint! Can you separate climate change from natural climate variability in a single climate record? PullbackDMDc is a method combining dynamical systems theory and data-driven modelling to do exactly that. 👉 buff.ly/MdUlqqk

💡 New paper! How does 🔥 wildfire risk in Southern Europe change by 2100? Using ML, climate & land-use, wildfire risk increases strongly under high-emission SSP3-7.0. Future land use and population changes significantly shape the projected risk. 👉 buff.ly/rFeObPM

📢 New preprint! Introducing DROP 💧 a physically informed deep learning framework for river discharge prediction. DROP delivers: ✅ Strong spatial generalization ✅ Better flood peak prediction ✅ Interpretable, spatially explicit diagnostics 👉 doi.org/10.22541/au.17641092…

💡 New Paper! Why do observed and simulated winter precipitation trends often disagree? Our study shows that models capture the warming-driven response well, but often underestimate changes in atmospheric circulation, especially in the Mediterranean. 👉 doi.org/10.1038/s41586-026-1…

💡 New Paper! Can AI improve how ESMs represent clouds? We present a hybrid ML radiation scheme that learns radiative impact of subgrid-scale clouds from 5 km storm-resolving simulations. ✅ 4–10× lower errors than conventional radiation schemes. 👉 buff.ly/nxo8Wdm

⏰ #AI4PEX Science Talks this Thursday! 🌍 Hadi Shokati AI for soil erosion, flood segmentation & rainfall erosivity forecasting 🧠 René Geist SoftJAX & SoftTorch: differentiable programming for scientific ML 📅 25 June 2026, 13:00 CEST 👉 Register now! survey.academiccloud.de/f/66…

💡 New Paper! ⛵ Can sailboats improve estimates of the ocean CO₂ sink? Citizen-science measurements help reveal a stronger Southern Ocean sink, but current sampling is still too sparse to fully constrain long-term trends. 👉 buff.ly/FfqGxiZ

🎓 Next up in the #AI4PEX Science Talks! 🌍 Hadi Shokati AI for soil erosion, flood segmentation & rainfall erosivity forecasting 🧠 René Geist SoftJAX & SoftTorch: differentiable programming for scientific ML 📅 25.06.2026, 13:00 CEST 👉 Register now! survey.academiccloud.de/f/66…

🎥 Looking back at the ELLIS Winter School 2026 in Athens! A week full of AI, climate science, hands-on projects, & inspiring discussions. 🌍🤖 Watch the full highlight video: ai4pex.org/blog/Winterschool… Special thanks to Olyvon for producing this video.

💡 New Paper! 🌡️ How much of recent summer warming is circulation-driven? Our new study shows that atmospheric circulation trends explain up to 50% of Europe’s summer warming — with strong but contrasting effects across the northern mid-latitudes. 👉wcd.copernicus.org/articles/…

💡 New Paper on global plant functional diversity 🌍🌿 Using remote sensing, biodiversity & trait databases, we map key plant traits worldwide at 1-km resolution — offering new insights into ecosystem functioning, biodiversity & resilience. 🛰️🌱 👉 nature.com/articles/s41467-0…

🌍 AI4PEX 2nd General Assembly in Brest, France! The week combines scientific exchange, collaboration & hands-on sessions on CNNs, AI agents, Generative approaches & Uncertainty Quantification. A highlight: dedicated discussions for ECRs on careers, funding & supervision.