IBM's AI can predict how we'll react to the weather

The "Deep Thunder" model will result in better micro-regional forecasts, too.


According to the "butterfly effect" theory, weather is inherently hard to predict. But IBM thinks that if you throw even more computing smarts and data at it, you should be able to at least improve forecasts. Big Blue is marrying its own hyper-local weather models with global ones from (its own) The Weather Company and creating Deep Thunder, the best-named forecasting system ever. To analyze all the data, the company is building new deep-learning algorithms and training them using petabytes of historical data.

On top of providing forecasting, IBM will help businesses by relating other data to the weather. With forecast accuracy down to 0.2 to 1.2 miles of resolution, it can tell companies in very fine detail how the weather affects things like consumer buying behavior, so they can stock and market products appropriately. Utility companies can also use the data to figure out if telephone poles will be damaged in a storm so they can plan accordingly, for instance.

The business forecasting helps companies quantify our behavior better than ever, in case you thought we weren't being tracked enough already. But improved weather forecasts will be particularly useful with the recent severe weather weirdness due to climate change. "The new combined forecasting model we are introducing today will provide an ideal platform [to help us] understanding the impacts of weather ... for all kinds of businesses and industry applications," says The Weather Company's Mary Glackin.