Source: WUNC, 5/4/21


Every spring, researchers publish their projected forecasts of the upcoming hurricane season – how many storms may form, and how severe they may be. But what if you could create these forecasts up to a year and a half in advance? A new model from North Carolina State University incorporates machine learning to create long-range hurricane forecasts with similar accuracy to those currently in use. Most preseason hurricane predictions are made using statistical models that use data from sea level pressure, sea surface temperatures, and other historical information.

For more of this story, click here.