IBM, The Weather Company use machine learning to predict impact of weather

Their new, hyper-local predictive model, called Deep Thunder, will use historical weather data to train machine learning models.

Several months after acquiring The Weather Company's B2B data business, IBM is showing how it's putting that data to work.

The Weather Company on Wednesday announced it's launching a hyper-local, short-term custom forecaster called Deep Thunder. The new predictive model will use historical weather data to train machine learning models, which will help businesses better predict the real-world effects of weather.

read more

Big Data Analytics

Big data could revolutionize analytics, databases and enterprise IT.

Read More

Data sets like The Weather Company's have become increasingly valuable for tech companies focusing on A.I. and analytics tools -- as demonstrated this week by Microsoft's purchase of LinkedIn and the subsequent rise in shares of Twitter. IBM first forged a pact with The Weather Company in March of last year, when it created its Internet of Things (IoT) unit.

Already, The Weather Company analyzes more than 100 terabytes of third-party data daily, and businesses around the world use its regional models to get new guidance every three hours. The new models, developed by IBM Research, are highly customized for business clients and have zeroed in on hyper-local forecasts, at a 0.2 to 1.2 mile resolution. They also take into account other environmental data like vegetation and soil conditions.

"The Weather Company has relentlessly focused on mapping the atmosphere, while IBM Research has pioneered the development of techniques to capture very small scale features to boost accuracy at the hyper local level for critical decision making," Mary Glackin, head of science & forecast operations for The Weather Company, explained in a statement.

Deep Thunder will also use machine learning-based weather impact models to help businesses predict the impact of even modest variations in temperature. For instance, a retailer could more accurately determine how it should stock shelves in anticipation of changed consumer behavior, insurance companies could more accurately assess the validity of insurance claims, or a utility company could better manage its repair crews.

"The new combined forecasting model we are introducing today will provide an ideal platform to advance our signature services - understanding the impacts of weather and identifying recommended actions for all kinds of businesses and industry applications," Glackin said.

Newsletters

You have been successfully signed up. To sign up for more newsletters or to manage your account, visit the Newsletter Subscription Center.
See All
See All