In a move to combat the growing challenges of extreme weather, the U.S. National Aeronautics and Space Administration (NASA) has chosen Planette, a long-range weather prediction technology company, to develop QubitCast, a next-generation forecasting system.
QubitCast is powered by artificial intelligence (AI) designed to improve long-range or subseasonal-to-seasonal (S2S) forecasts, which extend from two weeks to two years.
This is a significant step, Planette notes, as unlike conventional weather modeling, which is limited to ten days of lead time, its layering of several physics-based models and AI enables its forecasts to extend beyond this window.
Planette combines atmospheric data with ocean and land inputs and couples this modelling approach to fill a critical information gap between traditional short-term weather predictions and long-term climate projections, up to one year into the future.
QubitCast uses quantum physics principles on conventional computers, an approach that allows the system to process data more efficiently and uncover hidden patterns in Earth’s climate
“Planette is one of the first companies to take these methods beyond theory and apply them to weather and climate,” said Dr. Kalai Ramea, co-founder and Chief Technology Officer of Planette.
Adding: “You can think of it like reading the entire history of Earth’s systems all at once. Instead of slowly scanning year by year and missing critical details, our approach allows us to spot anomalies, those needles in the haystack that signal extreme weather events, much faster and more accurately than traditional AI models ever could, while using far less energy.”
Current long-term weather models utilize massive physics-based simulation models that are powerful but expensive and energy-intensive. There are also AI models that attempt to understand Earth’s systems but become overwhelmed by complex, high-dimensional data, requiring even more computational power and time.
QubitCast can address these issues thanks to its quantum-inspired approach on conventional computers, Planette explains. It needs less energy and computing power while still going through complex information to find hidden patterns in Earth’s systems.
This technology approach, Planette highlighted, makes it better at detecting extreme weather events early and providing actionable warnings.
A system like QubitCast can help re/insurers to address a number of challenges arising from a changing climate.
For example, it can help to improve risk assessment and pricing thanks to its more accurate view of future risks. The expanded lead time provided by its long-range and S2S AI-powered forecasts could help insurers better calculate the probability of cat events and price policies accordingly.
QubitCast more accurate forecasting could also be used to incentivise risk mitigation, which in turn could help reduce the total cost of claims and make insurance more affordable for customers, among other benefits.
About the Author
