Imagine having a super-detailed digital map of the Earth that doesn't just show the weather, but predicts when the planet's natural systems might suddenly break. It's like moving from a blurry photo to a 4K video of our climate's future. This helps us see exactly where and when extreme changes will hit, rather than guessing based on global averages.
Current climate models are too coarse to predict regional extremes or sudden 'tipping points' in nature. This leaves businesses and policymakers blind to specific local risks and the actual impact of exceeding global warming targets.
A new generation of high-resolution Earth system models (ESMs) and ML-based regional downscaling tools. They also created a catalogue of abrupt changes and new emission scenarios.
If you are a reinsurance firm dealing with unpredictable extreme weather losses — this project developed high-resolution Earth system models that provide better data on regional extremes. This allows for more accurate pricing of risk for assets in areas prone to abrupt climate shifts.
If you are an agri-tech company dealing with shifting growing zones — this project developed ML-based regional downscaling that improves understanding of long-term changes. This helps in predicting crop viability and water stress at a local level.
If you are an energy developer dealing with site selection for wind or solar farms — this project developed new emission and land use scenarios. This provides a clearer picture of future regional climate stability to ensure long-term infrastructure resilience.
Based on available project data, no pricing or cost structure is mentioned as this is a Horizon-RIA research project.
The project focuses on developing a new generation of models and testing them against observations. Based on available project data, it is currently in the simulation and evaluation phase rather than a commercial product.
Based on available project data, there is no specific mention of licensing terms or patent filings for the ESMs and ML methods.
The project period runs from 2023-01-01 to 2027-12-31, with results being delivered throughout this window.
The project uses machine learning (ML) for regional downscaling, which typically allows for integration into data pipelines, though specific API or integration protocols are not detailed in the data.
The consortium is heavily weighted toward research and academia, with 11 research organizations and 7 universities. However, the inclusion of 2 industry partners and 1 SME suggests a bridge toward commercial application. The 9% industry ratio indicates the project is primarily driven by scientific discovery with a secondary focus on practical implementation.
Contact SVERIGES METEOROLOGISKA OCH HYDROLOGISKA INSTITUT
Contact us to explore how these high-resolution climate models can be applied to your risk assessment strategy.
