How Critical is AI Weather Forecasting to the Global Economy?
Weather prediction is one of the most challenging–scientific endeavors.
Traditionally, weather forecasting uses computationally intensive physics-based models. As a result, they take a long time to run and are less accurate the more you go out in time to the 10-day or 14-day scale. Weather forecasts are improving, but 10-day forecasts are still less than 50% correct, per Our World In Data.
Artificial intelligence (AI) could make it more accurate.
Several companies are already using AI to enhance their model’s prediction accuracy and reduce their model run times. In Nov. 2023, Google announced GraphCast, its state-of-the-art AI model that delivers 10-day weather predictions at unprecedented accuracy in under one minute. Last week, Spire Global, a space-to-cloud data and analytics company that specializes in weather patterns, confirmed a partnership with Nvidia to use AI to increase the accuracy of its weather forecasting model.
While weather is important for consumers because it drives what you wear and your plans for the day, it’s much more critical to the global economy than you think. According to CNBC, a third of the global economy — roughly $30 trillion worth of global GDP — ranging from trade to agriculture to power generation is subject to weather.
In short, the need for more accurate forecasts is in high demand.
