๐ Next up in the #AI4PEX Science Talks!
๐ Hadi Shokati
AI for soil erosion, flood segmentation & rainfall erosivity forecasting
๐ง Renรฉ Geist
SoftJAX & SoftTorch: differentiable programming for scientific ML
๐ Thursday, 25. June 2026 at 13:00 CEST
Join us for a deep dive into Earth observation, AI & scientific machine learning.
๐ Register now! https://survey.academiccloud.de/f/668874?lang=en
๐ฅ Looking back at the ELLIS Winter School 2026 in Athens!
A week full of AI, climate science, hands-on projects, inspiring discussions & new collaborations. ๐๐ค
Watch our highlight video and hear from participants, instructors & organizers.
Special thanks to Olyvon for producing this amazing video and supporting the school.
๐ก New Paper on global plant functional diversity ๐๐ฟ
Using remote sensing, biodiversity observations & trait databases, this study maps key plant traits worldwide at 1-km resolution โ offering new insights into ecosystem functioning, biodiversity & resilience under environmental change. ๐ฐ๏ธ๐ฑ
๐ https://www.nature.com/articles/s41467-026-72111-6
#AI4PEX #Ecology #RemoteSensing #Biodiversity #EarthObservation
๐ 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 โ followed by a beautiful coastal hike ๐
Thanks to for hosting us!
๐ก New Paper on physics-aware AI for #EarthObservation ๐๐ค
By combining physical models with symbolic regression & sparse ML, this work moves toward more interpretable and trustworthy emulators for atmospheric radiative transfer.
๐https://doi.org/10.1109/TGRS.2026.3676858
A step toward explainable AI in Earth system science ๐
๐ค #EGU26 Spotlight
AI must go beyond prediction ๐
Gustau Camps-Valls on AI for climate resilience โ from explainable AI to early warning systems & causal models.
๐ https://meetingorganizer.copernicus.org/EGU26/EGU26-22994.html
๐ค #EGU26 Spotlight
Climate extremes donโt always happen alone ๐ก๏ธ
Sonia Seneviratne on compound events โ rising risks, near-permanent extremes, and limits to adaptation. How multiple climate extremes interact & amplify impacts.
๐ https://meetingorganizer.copernicus.org/EGU26/EGU26-14314.html
๐ค #EGU26 Spotlight
How do soil moisture & temperature drive extremes? ๐
Feini Huang combines causal AI + ML to disentangle landโatmosphere feedbacks โ and benchmark climate models.
๐ https://meetingorganizer.copernicus.org/EGU26/EGU26-12361.html
๐ค #EGU26 Spotlight
Are AI climate models really more efficient? ๐ค๐
Tom Beucler compares AI, hybrid & GPU-based models โ and finds the advantage isnโt always clear-cut.
๐ https://meetingorganizer.copernicus.org/EGU26/EGU26-18440.html
๐ค #EGU26 Spotlight
Some regions are โbehindโ or โaheadโ in warming ๐ก๏ธ
Dominik Schumacher shows: areas lagging today may see faster rises in extreme heat soon.
๐ https://meetingorganizer.copernicus.org/EGU26/EGU26-13840.html
AI4PEX