Could NASA's Quantum Theory AI Change Meteorology Forever?
NASA is partnering with San Francisco-based weather prediction company Planette to develop 'QubitCast', an innovative quantum-inspired AI system designed to predict extreme weather events months in advance.
The collaboration addresses a critical limitation in current forecasting capabilities, where meteorologists face challenges in providing accurate predictions beyond a 10-day window.
While some organisations offer two-week forecasts, maintaining accuracy for longer periods remains problematic.
Quantum-inspired AI: A new approach to weather prediction
QubitCast leverages algorithms inspired by quantum physics principles, particularly the concept of exploring multiple possibilities simultaneously.
This innovative approach enables efficient processing of vast amounts of atmospheric, ocean and land data.
"You can think of it like reading the entire history of Earth's systems all at once," says Dr Kalai Ramea, Co-Founder and CTO of Planette.
"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."
The technology operates on conventional computers rather than requiring specialised quantum computing hardware, making it more accessible and practical for implementation.
Enhanced computational efficiency through AI
Traditional physics-based simulation models require substantial computational resources, while current AI models struggle with complex, high-dimensional Earth system data.
QubitCast addresses these challenges by delivering accurate predictions with reduced computing power and energy consumption.
The system's quantum-inspired methodology simplifies complex information while maintaining essential details for accurate forecasting, making long-range weather prediction more accessible and cost-effective.
Business applications and impact
"Too many critical decisions are made in the dark because reliable long-range forecasts have not been available," explains Dr Hansi Singh, Co-Founder and CEO of Planette.
"QubitCast transforms that equation by making S2S forecasting not just more accurate but practical to deploy at scale when making highly consequential decisions."
The technology focuses on subseasonal-to-seasonal forecasting, covering predictions from two weeks to two years ahead. Its applications span multiple sectors, including agricultural planning, emergency management, and energy grid stability.
The partnership is part of NASA's Small Business Innovation Research grant programme. Planette has already demonstrated success with its NIVA AI model for Earth system analysis and launched Eddy, offering free long-range weather predictions to the public.
The company aims to connect short-term weather reports with long-term climate projections, providing insights from one week to six months ahead, with plans to extend to multi-year forecasts.
