💡 New Paper Out!
#MachineLearning (ML) improves #EarthSystemModels, but explaining its added value is tough. Inspired by climate model hierarchies, we propose using Pareto-optimal models to distill ML's added value in representing cloud cover, radiative transfer and tropical precipitation.
👉 Find out more: https://arxiv.org/abs/2408.02161#
#ClimateResearch
#EarthSystemModels
What are the climate models we are working on? Land model number 3:
ORCHIDEE (Organising Carbon and Hydrology In Dynamic Ecosystems), the land surface model of the IPSL #EarthSystemModels, where our focus is especially on the hydrological processes.
👉 Learn more: https://buff.ly/83X23ho
What are the climate models we are working on? Let’s start with the land models:
JULES, the Joint UK Land Environment Simulator: a community land surface model that can be coupled to the Met Office Unified Model where we will build high-dimensional emulators to calibrate land surface behavior.
👉Learn more: https://buff.ly/ZJY5eZJ
What are the climate models we are working on? Let’s start with the land models:
LPJ-GUESS from Lund University, is a process-based dynamic vegetation-terrestrial ecosystem model where we focus on forest dynamics.
👉 Learn more: https://buff.ly/kJQxy5H
📢Exciting news! #AI4PEX is now on Bluesky!
👉Connect with us at ai4pex.bsky.social for the latest project news and stay up to date with our research.
#ClimateResearch #HorizonEU #Bluesky #EarthObservation #EarthSystemModels
It's a powerful endorsement of model fidelity and utility when such features emerge as a natural result of model operation.
"CMIP6 models and ECCO are in agreement at the surface with supergyres connected across all basins but present some differences at depth in both position and strength."
https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2024JC021140?af=R
#AI4PEX research focus 2: Model Development
To develop better #EarthSystemModels we will expand the use of #EarthObservation in combination with #MachineLearning. We focus on explainability of #AI models and causality to better identify model-observations mismatch.
#AI4PEX research focus 1: #EarthObservation
We use existing in-situ observations and satellite data to generate new upscaled #MachineLearning-based products, and cross-check for with the #Copernicus land, ocean and atmospheric datasets.
🌊Nowadays, #EarthSystemModels allow #ClimateScientists to simulate various ocean processes, including swirling currents called eddies. This advancement is thanks to improved model resolution🌀
🔎Studying high-resolution simulations is crucial for understanding #ocean dynamics. A recent blog post, for example, explored a study that sheds light on how human-induced #ClimateChange impacts #OceanEddyActivity
🤔 Intrigued? Read our full article here: https://buff.ly/49mc7iw
🌐 Global simulations developed by #nextGEMS at the km scale are being used to understand critical Earth System dynamics in the land-based water cycle. These simulations capture details like rainfall patterns and the resulting river discharges🌧️ , which serve to evaluate the water balance of specific regions, such as the Rhine basin.
📽️ Learn more about our #EarthSystemModels in this Science Explainer.
📣 #AI4PEX just launched its new website 🚀.
Check it out 👉 https://ai4pex.org/
🔷 One of our main tasks at #nextGEMS is accurately representing land heterogeneity using #EarthSystemModels. That's why one of our key thematic areas is "Storms & Land"
Today, we’re excited to share more about this through an explanatory video! 📽️
In the video, Cathy Hohenegger from the Max Planck Institute for #Meteorology discusses the objectives of this theme and highlights some of the potential outcomes.
👉 Watch the video here: https://nextgems-h2020.eu/media-library/?medium_id=381
Our 4-year project is conducted by a consortium of 19 partners from all over Europe bringing together an interdisciplinary team of experts to bridge #EarthObservation and #EarthSystemModels via advanced data science approaches.
#AI4PEX is a transnational #ClimateResearch project funded by #Horizon2EU #CINEA. We will deliver enhanced knowledge on the Earth System by integrating #EarthObservation, #ArtificialIntelligence and #MachineLearning into Earth System modelling.
#AI4PEX postdoc position available @MPI_BGC developing hybrid modeling approach (HM) bridging machine learning and #EarthSystemModels!
See here: https://www.mpg.de/21834237/postdoctoral-researcher-m-f-d4
Welcome to the new #HorizonEU project AI4PEX.
#AI4PEX aims to harness AI to improve Earth System modelling to increase the accuracy of #ClimateChange projections and support for implementation of the Paris Climate Agreement and the #EUGreenDeal. 🌱
🚀 Join us on this journey. Follow for updates and insights!
My expert hour at #egu24 at 12-13:00 today at the #DKRZ booth.
Happy to talk about the global carbon cycle and the #ocean #carbonsinks and how we model all this with our #EarthSystemModels.
#CLICCS
Interested in atmospheric blockings? 🤔 Picture them as sky traffic jams! 🚗 Sometimes, high-pressure systems act like roadblocks, stalling weather patterns and prolonging certain conditions like rain, heat, or cold. 🌦
Today, we had a fascinating talk with Edgar Dolores Tesillos from the #UniversityofBern. He explored Atmospheric Blockings, their significance in #EarthSystemModels, and their link to extreme #weather.🌡️
#StormsResolving #nextGEMS #ClimateChange #ClimateScience #H2020 @cinea_EU
Did you know that #TropicalCyclones are one of the most costly natural hazards? 😱
🌀Hence, better tropical cyclone simulations in #EarthSystemModels also mean better understanding of their physical and societal effects. Climate scientist Alex Baker, a project partner from Uni Reading (UK), elucidates further in our latest blogpost about how #nextGEMS is revolutionizing cyclone simulations.
Let us know your thoughts in the comments below! 💬
https://buff.ly/3TNNLHZ
#H2020 #Weather @cinea_EU
✅ Our 4th km-scale #Hackathon has officially ended! Lots of successes to celebrate and challenges ahead, but we’re happy to see our community growing and developing unbelievable tools for #ClimateScience 🌐
As part of the closing sessions, participants engaged and shared their opinions and concerns regarding the #EarthSystemModels, future publications, and collaborations between #ClimateModelling projects in an open discussion panel and after the event at @MPI_Meteo
Supported by @cinea_EU
Client Info
Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst