Natural disasters can happen in the blink of an eye, leaving a devastating trail of debris and memories.  Some say that these tragedies can be prevented lessened, if only we had better technology to predict natural disasters and steer clear.

With the hype surrounding Big Data, the thinking is that such technology could help predict tornados like the one that recently hit Oklahoma, or hurricanes, so that authorities can provide earlier warning to avoid casualties.

People in Moore, Oklahoma only had 14 minutes to brace themselves before the tornado struck.  Minutes after the sirens blasted everything was in utter chaos.  Twenty-four people were killed in the tragedy, seven of those were 8- and 9-year-old students at Plaza Towers Elementary School in Moore.  If people had received an earlier warning, some of these 24 death may have been averted.

Can Big Data really protect us from Mother Nature?

According to Kelvin Droegemeier, the VP of Research for the University of Oklahoma, the answer is yes -Big Data can be used to accurately predict weather anomalies and give earlier warnings to residents.  Droegemeier explained that by using a model of a tornado outbreak in central Oklahoma from 2011, a computer model was created and predicted nearly the exact path of two tornadoes that had touched down the same year.  The numerical forecast was the basis of the computer model that showed the rotation of the storm and though the system was not entirely flawless, it was able to make the predictions a full hour before the tornadoes hit.

The question now is, if the technology exists, is tested and fount to be quite effective, how come it’s not being widely used?  Funding is certainly an obstacle for such research-intensive initiatives.  And as with anything leveraging the scientific method, more tests need to be done on data-driven technology and its role in alerting (and sometimes evacuating) large populations of people.

Companies are also utilizing Big Data to predict weather and use the information to predict market trends, like what EarthRisk did in the winter of 2011-12.  Traders in the natural gas market expected the weather to be cold, which would drive prices up.  But EartRisk’s models showed that the atmosphere wasn’t likely to get as cold as expected.  This in turn resulted in their clients making money when natural gas prices in fact declined.

IBM’s Deep Thunder, a local weather forecasting method that focuses on “operational problems that weather can present to businesses in very specific locales.”

“We start with a client’s business problem,” said Lloyd Treinish, chief scientist of the program for IBM Research. “Clients indicate to us what kind of lead time they need to be more proactive. … For a utility company, for instance, it’s all about how quickly the power can be restored. And that requires resources. If we understand the nature of not just the impending weather events but the outages caused by the damage they cause—and the kinds of people and equipment needed to restore that power, then [clients] can be prepared.”

Deep Thunder is heading to Rio de Janeiro and will be used to better anticipate flooding, and predict where mudslides might be triggered by severe storms.

Infographic

John Nelson created Tornado Tracks, an infographic showing 56 years of tornado tracks in the US.  The neon blue streaks that look like it was doodled on by a kid represents all the tornado tracks in the country.  notice how almost all of them are concentrated East of the Rocky Mountains?

Tornadoes are created when there is a mixing of cool and warm air or landfalling of a cyclone.  During winter months, tornadoes are usually spotted in the Southern area of the country, as well as states near the Gulf of Mexico, as cold air moves southward reaching its southern limit of expansion, and stopping over the Gulf Coast.  During spring, hot air progressively moves back into the Gulf Coast and pushes the mass of colder air forward, out of the Gulf States and into the Southeastern states.

Tornadoes can be created anytime, but March through August is considered as tornado season.

The infographic showed how often a certain place is hit by a tornado, the more the streaks glow, the more frequent it is hit by a tornado.  It also showed the number of injured and deaths during some periods.

photo credit: Lori Joan via photopin cc