Hadoop is the leading database engine among companies today, and many have realised just what is possible through its ability to store and process enormous amounts of data. Below are two use cases of Hadoop that are preventing suicides among military veterans and helping farmers manage their production.

1) Combatting Suicide In The Military

In 2012, it was reported that military suicides were double the rate of military personnel killed in combat. Last year, the Iraq and Afghanistan Veterans of America (IAVA) conducted a survey of 4,104 veterans to better understand these suicide rates. It found that 30 percent of respondents had considered suicide, 45 percent knew an Iraq or Afghanistan veteran who had attempted suicide and 37 percent knew a veteran who had actually committed suicide.

In response to this, predictive analytics firm Patterns & Predictions created the Durkheim Project. Using Cloudera’s distribution of Hadoop, the Durkheim Project performs advanced analytics, machine learning, and real-time predictive modeling, to identify correlations between veterans’ communications and potential suicide attempts.

Phase 1 of the project concluded in early 2013 and saw 65 percent accuracy in predicting suicide risks.  Phase two launched in July 2013 and is trying to get 100,000 veterans to opt in to the study. “Participants who opt in receive a unique Facebook app and a mobile app designed to capture posts, Tweets, mobile uploads, and even location. Additional profile data is captured as well, including physician information and clinical notes.”

Although the Durkheim Project is only allowed to monitor and analyze data (it does not have permission to intervene with these suicide attempts), Chris Poulin, the founder of P&P said, “one of the promises of Big Data in this case is that you can shorten the distance between the people who need help and the system that can get them help.”

2) Helping Farmers Deal With Climate Change

Climate Corporation, which was acquired by Monsanto for more than $1 billion last year, is using Hadoop to build a system that can successful create weather projections for the next two years at every 2.5 by 2.5 kilometre grid across the U.S.

Through their proprietary technology platform – which combines hyper-local weather monitoring, algorithmic data modelling, and weather stimulations – Climate Corp. can map out the most likely 10,000 outcomes per location to create the most probable outcome of the weather.

“We are proud of using Hadoop to provide a class of weather insurance for farmers never before available and to do it in a way where, with index-based weather insurance, farmers have access to an independently sold product that changes how they manage risk,” said Andy Mutz, director of engineering for Climate Corp. “Since 85 percent of farmers’ risks are weather related, this is our impact on the world.”

According to one report, the company’s technology ingests weather measurements from 2.5 million locations and 150 billion soil observations to generate 10 trillion weather simulations. Accordingly, the company manages over 50 terabytes of live data in its systems at any given time.

Read more here

(Image Credit: Rilind Hoxha)


Previous post

IBM's Watson Mobile Developer Challenge Winners Announced

Next post

DataTorrent RTS Released, Processes 1 Billion Data Events a Second