Deep Thunder: weather analysis project for iPad and cloud applications


In 1996, IBM began exploring the “business of weather,” hyper-local, short-term forecasting and customized weather modeling for clients. Now new analytics software, and the need for organizations from cities to energy utilities to operate smarter, are changing the market climate for these services.
As Lloyd Treinish, chief scientist of the Deep Thunder program in IBM Research explains, this approach isn’t about the kind of weather reports people see on TV, but focuses on the operational problems that weather can present to businesses in very specific locales—challenges that traditional meteorology doesn’t address.
For example, public weather data isn’t intended to predict, with reasonable confidence, whether three hours from now the wind velocity on a 10-meter diving platform will be acceptable for a high stakes competition. That kind of targeted forecasting was the challenge that IBM and the US National Oceanic and Atmospheric Administration (NOAA), parent of the US National Weather Service, took on in 1995.

Storm damage in Rio de Janeiro
The storm and mudslides in Rio de Janeiro on April 6, 2010 left over 200 dead and thousands homeless. The event prompted the city to start planning the development of central emergency operations center to include Deep Thunder forecasting and other capabilities.
Treinish, who joined IBM Research in 1990 after 12 years at NASA’s Goddard Space Flight Center in Maryland, recalls that the collaboration required forecasts with time horizons of a few hours or a day. Such precision prediction of what the weather will be in a very particular place, at a very particular time, focused on particular applications isn’t the core mission of government weather services, which concentrate on forecasting, warning and monitoring weather from the regional to the global scale for general use
IBM and NOAA scientists decided to collaborate on the challenge, and built one of the first parallel processing supercomputers to be used for weather modeling. The system, based on the IBM ® RS/ 6000 ® SP and installed at the National Weather Service forecasting office in Peachtree City, Georgia, ran software adapted from NOAA, Colorado State University and IBM for several months in 1996, producing multiple forecasts each day.
A year later, the IBM Deep Blue ® system played and defeated the world chess champion in May, 1997. The name inspired a journalist to dub the IBM weather project Deep Thunder in November. The name stuck.
The project, which was originally set up in the IBM Research department known as Mathematical Sciences (now called Business Analytics and Mathematical Sciences), pivoted from a hardware focus to services and software. “We learned that the business driver was the most important factor,” says Treinish. “And we started to focus on niche business problems that were weather sensitive and look for the market gaps we could fill.”
For example, with the right combination of precision weather prediction and business analytics insights, airlines and airports could better manage the logistical nightmare of weather-generated delays. Flights could be re-routed or consolidated more efficiently.
Equipped with highly specific information on wind, temperature and other factors, fire fighters could battle wildfires more effectively.
Indeed, since serving highly specific regions was central to the business-of-weather strategy, in 2001, the team set up a testbed in its own backyard, the New York City metropolitan area. This living laboratory was a 3D grid of thousands of blocks, each one cubic kilometer in size. Calculations could be run on each cube of the grid to generate very local and precise predictions.
The team also began working on the kind of modeling, forecasting, and data visualization innovations that could help a business make smarter logistical, planning and operational decisions, faster and with more confidence.
For example, to help a utility company prepare for the after effects of a major storm, the team could mine and model historical data of what kind of damage was caused to power lines or telephone poles, and why. By coupling that with a hyper-local forecast, IBM could help a company plan for how many repair crews would be needed, and where.
The Deep Thunder group has also been able to dovetail with other analytics-driven projects such as Smarter Cities. Working with colleagues in the new IBM Research center in Brazil as well as the IBM India Research Lab, the team is leading the Rio de Janeiro project to better anticipate flooding, and predict where mudslides might be triggered by severe storms. Here again, highly targeted weather modeling is only part of the story. Through a new city command center, weather data can be integrated with other city information systems to determine how best to respond to such situations, including where and when to deploy emergency crews, make optimal use of shelters and monitor hospital bed availability.
With the 2014 World Cup in Rio, the forecast for the business-of-weather approach pioneered by Deep Thunder was witnessed.


One Comment to “Deep Thunder: weather analysis project for iPad and cloud applications”

  1. It’s actually a great and helpful piece of info. I am glad
    that you just shared this helpful info with us.
    Please keep us up to date like this. Thank you
    for sharing.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: