#ai4pex — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #ai4pex, aggregated by home.social.
-
📢 New preprint!
Introducing DROP 💧 a physically informed deep learning framework for river discharge prediction.
By combining AI with explicit river routing, DROP delivers:
✅ Strong spatial generalization
✅ Better flood peak prediction
✅ KGE improvement from 24% → 62%
✅ Interpretable, spatially explicit diagnosticsA scalable approach for hydrological forecasting and flood risk assessment.
👉 https://doi.org/10.22541/au.176410929.91946608/v1 -
⏰ Reminder: The next #AI4PEX Science Talks take place this Thursday!
🌍 Hadi Shokati
AI for soil erosion, flood segmentation & rainfall erosivity forecasting
🧠 René Geist
SoftJAX & SoftTorch: differentiable programming for scientific ML📅 Thursday, 25 June 2026
🕐 13:00 CESTJoin us for a deep dive into Earth observation, AI & scientific machine
learning.
👉 Register now! https://survey.academiccloud.de/f/668874?lang=en -
🎓 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📅 Thursday, 25. June 2026 at 13:00 CEST
Join us for a deep dive into Earth observation, AI & scientific machine learning.
👉 Register now! https://survey.academiccloud.de/f/668874?lang=en -
🎥 Looking back at the ELLIS Winter School 2026 in Athens!
A week full of AI, climate science, hands-on projects, inspiring discussions & new collaborations. 🌍🤖
Watch our highlight video and hear from participants, instructors & organizers.
Special thanks to Olyvon for producing this amazing video and supporting the school.
-
💡 New Paper on global plant functional diversity 🌍🌿
Using remote sensing, biodiversity observations & trait databases, this study maps key plant traits worldwide at 1-km resolution — offering new insights into ecosystem functioning, biodiversity & resilience under environmental change. 🛰️🌱👉 https://www.nature.com/articles/s41467-026-72111-6
#AI4PEX #Ecology #RemoteSensing #Biodiversity #EarthObservation
-
🌍 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 — followed by a beautiful coastal hike 🌊
Thanks to for hosting us!
-
💡 New Paper on physics-aware AI for #EarthObservation 🌍🤖
By combining physical models with symbolic regression & sparse ML, this work moves toward more interpretable and trustworthy emulators for atmospheric radiative transfer.
👉https://doi.org/10.1109/TGRS.2026.3676858
A step toward explainable AI in Earth system science 🚀
-
🎤 #EGU26 Spotlight
AI must go beyond prediction 🌍
Gustau Camps-Valls on AI for climate resilience — from explainable AI to early warning systems & causal models.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-22994.html
-
🎤 #EGU26 Spotlight
Climate extremes don’t always happen alone 🌡️
Sonia Seneviratne on compound events — rising risks, near-permanent extremes, and limits to adaptation. How multiple climate extremes interact & amplify impacts.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-14314.html
-
🎤 #EGU26 Spotlight
How do soil moisture & temperature drive extremes? 🌍
Feini Huang combines causal AI + ML to disentangle land–atmosphere feedbacks — and benchmark climate models.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-12361.html
-
🎤 #EGU26 Spotlight
Are AI climate models really more efficient? 🤖🌍
Tom Beucler compares AI, hybrid & GPU-based models — and finds the advantage isn’t always clear-cut.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-18440.html
-
🎤 #EGU26 Spotlight
Some regions are “behind” or “ahead” in warming 🌡️
Dominik Schumacher shows: areas lagging today may see faster rises in extreme heat soon.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-13840.html
-
🎤 #EGU26 Spotlight
Fires, beetles… or management? 🌱
Thomas Pugh shows that harvest decisions may shape Europe’s forests more than disturbances.🔗 https://meetingorganizer.copernicus.org/EGU26/EGU26-17236.html
-
🌍 AI is transforming climate modelling!
Catch us at #EGU26 presenting work on AI climate models, hybrid approaches & scaling
⚡️ Don’t miss: Beucler, Grundner, Ivanov, Camps-Valls + more!
-
3 days, 9 models, 1 goal: benchmarking mortality in #EarthSystemModels 🌍
From data & model overviews to hands-on coding sessions, we worked toward a shared framework, common metrics, and first results for a joint paper.
Great collaboration across teams & time zones! 🚀
-
Day 1 of the ELLIS Winter School: AI for Earth System, Hazards & Climate Extremes in Athens 🇬🇷
Keynotes on early warning of climate risks and the planetary data layer for an observable Earth, plus a powerful talk from Zisoula Ntasiou (Hellenic Fire Service) on how science and AI tools can support firefighters making decisions in the field.
Excited for the week ahead!
-
#AI4PEX postdoc position available at @unituebingen developing #MachineLearning approaches to improve #EarthSystemModels!
👉Join our team: https://uni-tuebingen.de/de/290466
-
🧩 Meet some of the challenges tutors guiding the problem-solving sessions of the Joint Winter School “AI for Earth System, Hazards & Climate Extremes”.
This Winter School brings together an exceptional group of tutors from the National Technical University of Athens (NTUA) and the Max Planck Institute for Biogeochemistry.
🌐 Discover the full tutor profiles on the website: https://ai4pex.org/Training/School2026/
-
⏳ The countdown is on!
Only one week left to register to the Joint Winter School “AI for Earth System, Hazards & Climate Extremes” (March 16 – 20 2026, NTUA Athens).Join us for an inspiring week of lectures, hands-on sessions, and collaboration where AI meets climate extremes to tackle some of today’s biggest challenges.
Register now 👉 https://ai4pex.org/Training/School2026/
#AIWinterSchool2026 #AI4PEX #MeDiTwin #ClimateAction #Networking #CINEA_EU
-
🎉 Tuesday is social day at the Joint Winter School! We’ll explore Ancient Lavrion — a UNESCO Tentative World Heritage Site — and end the day with 🔭 Stargazing, 🎶 Greek music and food, and relaxed networking. A perfect mix of science, culture, and connection. 🌙
🔍 More on Lavrion: https://buff.ly/060qqn0
#AI4PEX #MeDiTwin #AIWinterSchool2026 -
🧠 Meet the Zero To Hero tutors behind the AI Winter School!
Experts in AI, EO & climate analytics guiding hands-on sessions.📅 March 16–20, 2026, NTUA Athens Campus, Greece
🔗 Registration now open - https://buff.ly/dOFMhWy#AIWinterSchool2026 #AI4PEX #MeDiTwin #Mentorship #CapacityBuilding
-
🎤 Meet some of the inspirational speakers joining us at the Joint Winter School “AI for Earth System, Hazards and Climate Extremes” in March 2026!
🌟#Data - Ramón Fuentes Franco, SMHI
🌟#Modeling - Hongmei Li, Helmholtz Centre Hereon and Universität Hamburg
🌟#Trustworthiness - Gustau Camps-Valls, Universitat de València
🌟#Communication - Zisoula Ntasiou, Hellenic Fire Corps, Civil ProtectionFind out more: https://ai4pex.org/Training/School2026/
-
💡We’re thrilled to announce the Joint Winter School “AI for Earth Hazards & Climate Extremes”!
📍 NTUA Athens | 📅 March 16–20 2026
A week where AI meets climate science. Stay tuned!
-
Amazing time at Researchers’ Night at SMHI 🎉
It was inspiring to see such strong interest from enthusiastic people who stopped by to learn about #AI4PEX modeling, AI, data and clouds☁️🌊🌿
Great collaboration with OptimESM HE, TipESM & Climateurope2.💡
https://buff.ly/0ysJ0EC -
🌍 #ESMs have come a long way thanks to better computational power, data, and scientific understanding. But further enhancements are crucial as models still have a hard time simulating cloud formation, ocean-atmosphere interactions, and the role of biological processes in the carbon cycle. 🚀 That's where #AI4PEX teps in. Improving #ESMs is essential to get a better grip on what the future might hold and guide policy decisions.
👉 Follow us to catch all the exciting developments! -
🚀 First General Assembly for #AI4PEX in Lund!
Last month partners from across Europe met to advance #EarthSystemModels with #AI, #ML & #EarthObservation. 4 days packed with:
✨ Shaping benchmarking tools
🛠 Reviewing progress & syncing milestones
🌍 Boosting outreach & community building
🤝 Hands-on collaborationBig thanks to Lund University for hosting & to all driving this forward!
👉 www.ai4pex.org -
Fourth and last day of our #AI4PEX GA is again reserved for workshops.
Moderated by Fangfei Lan from UNIL we spend the morning focusing on Neural Operater Learning. In the afternoon, we build our own hybrid model using the SINDBAD modeling framework, led by Nuno Carvalhais from MPG-BGC.