Insurance
Home›Insurance›Reinsurance›AI could speed updates to catastrophe models for re/in…
AI could speed updates to catastrophe models for re/insurers
KCC says its Severe Convective Storm model processes more than 30 gigabytes of satellite, radar and weather data per day to generate hail and tornado or wind intensity footprints.
Karen Clark & Company, a catastrophe risk modelling firm, says artificial intelligence could reshape how catastrophe models are developed and refreshed, with knock-on effects for reinsurance pricing, underwriting and capital management. In an August 2026 white paper, KCC argues the industry is shifting from traditional statistical approaches toward physical models enhanced by AI.
KCC says the change is driven by the growing importance of more frequent weather perils, including severe convective storms, winter storms and wildfires, where historical data may not fully capture evolving risk. It also points to secondary perils, climate change and advances in science as factors increasing demands on the models used by reinsurers and insurers.
The company describes high-resolution physical modelling that uses atmospheric equations and large volumes of environmental data to simulate weather systems as they develop. It says its Severe Convective Storm model processes more than 30 gigabytes of satellite, radar and weather data each day and produces hail and tornado or wind intensity footprints.
KCC also cites its LiveEvents process, which has been running since 2018, to compare model estimates with actual claims and losses. The firm says the effort has created an archive of more than 100 terabytes of high-resolution atmospheric data, alongside tens of billions of dollars in claims data, and that AI-informed models could update in days rather than months.