We see an opportunity to blend our traditional hybrid, physical, and statistical approaches with a new set of tools that come from the world of artificial intelligence—specifically, machine learning—to develop a new framework for modeling weather and climate extremes. Our methodology combines a novel approach of de-biasing large-scale features in a computationally fast general circulation model (GCM), with analysis of fine-scale features from historical data to learn the "rules" of atmospheric behavior that produce weather extremes. Million-year catalogs will be possible—global catalogs that capture all types of dependencies, from global teleconnections to local correlations across all weather-related perils and across all regions.
When complete, our model will for the first time capture the planetary-scale atmospheric waves that can drive small-scale local extremes in a physically consistent manner across multiple regions and perils so that stakeholders can evaluate the global risk to their assets and portfolios for the next 10 years.
We continue to make significant investments in our modeling capabilities and our technology infrastructure to be effective, future-ready partners in this crucial endeavor.
For more information contact our Climate Change Practice.