Aeolus Capital Management Ltd., the specialist insurance-linked securities (ILS) and reinsurance investment manager, is researching and working with artificial intelligence tools to see how the technology can add detail to modelling of perils and aid in making risk selection decisions.Peter Dailey, Head of Research at Aeolus Capital Management described how the company is bringing artificial intelligence into its research and risk modelling process in a recent article.Dailey explains that Aeolus Capital Management is exploring how leveraging AI alongside the more traditional numerical weather prediction (NWP) models can add value through deeper insights.“NWP has distinct advantages tied to the physics embedded within the model, but is computationally expensive, especially in its ensemble mode.

AI can generate weather scenarios that lack the physics, but benefit greatly from efficiency.Can we combine the benefits without sacrificing their value?,” Dailey asks.He goes on to explain, “Forecast models can further benefit from the power of AI via forecast accuracy, which in the world of NWP requires increased spatial resolution of the ‘model grid’.

Where enhanced NWP accuracy comes at an enormous computational expense, AI models can provide the same forecast quality on a finer-scale grid without sacrificing computer time.“Here is where AI steps in to enhance an existing technology.Trained using huge volumes of historical weather and initialized with current weather observations, AI can develop an ‘ensemble of ensembles’, or a set of realistic scenarios spawned from a single NWP ensemble member.” Aeolus has already kicked-off an AI research project alongside State University of New York at Albany (SUNY Albany) earlier in 2025, focusing on the severe convective storm (SCS) peril.

The goal is to better understand the risks associated with tornadoes, hailstorms and severe thunderstorms, using a coupled NWP-AI model, with the AI component being the Google DeepMind developed AI-based weather forecast model GraphCast, Dailey explained.“While our initial application will be to SCS risk, GraphCast supports a wide range of weather risk applications including hurricane track prediction, the simulation of atmospheric rivers and associated winter storms, extreme temperatures, and the list goes on,” he added.Why this could be important, Dailey states that, “Coupled NWP-AI models, also known as machine learning–based weather prediction (MLWP) are trained from historical data offering an alternative to traditional NWP.

MLWP has the potential to dramatically improve forecast accuracy by capturing patterns that are not represented by the model physics.Such models also offer an opportunity to gain efficiency by exploiting modern AI-optimized hardware and strike a more favorable speed–accuracy balance.” For an ILS and reinsurance investment manager like Aeolus Capital Management, deeper insights into the risks being covered are a critical area for performance and also alpha generation these days.Dailey explained that, “Just as traditional NWP forecasts can only provide limited information about the ‘tail of the distribution’, catastrophe models provide a limited view of how strong and how often extreme events will occur in the future.

“Catastrophe modeling firms apply a combination of physical and statistical techniques to generate a large ensemble of potential future events.“Using AI, and the added detail it provides, can aid in decision-making around risk selection, pricing, and an array of underwriting and operational risk factors.” Bringing AI and advanced technology into the modelling and risk selection process is going to be critical for ILS investment managers.Now, there is technology available that can be used alongside the traditional catastrophe modelling tools the industry is so familiar with, to extend and enhance their output and provide additional insights to ILS portfolio decision-making.

Dailey’s article is quite technical so we’d recommend ..All of our Artemis Live insurance-linked securities (ILS), catastrophe bonds and reinsurance can be accessed online.Our can be subscribed to using the typical podcast services providers, including Apple, Google, Spotify and more.