Predict a volcanic eruption, save the lives of thousands.
That’s the kind of promise the Industrial Internet Of Things can make.
With investment in the Industrial Internet of Things forecast to be worth hundreds of billions of dollars over the next decade, the key to its success will be how companies or people leverage the data being generated.
Predictive asset maintenance reduces the chances of an operation going offline, with an increasing number of industrial companies moving away from the traditional react-and-fix model. It’s better to know when and how something will break than reacting after it does. At the same time, industrial assets are always susceptible to elements beyond their control with the weather playing a significant role.
Being able to predict and prepare for extreme weather is part of planning for potential failure within the Industrial Internet of Things … but Mother Nature is not just about wind, rain and snow. Every now and again she likes to throw something special into the mix.
A volcanic eruption, for example.
GE Reports said that a digital early warning system for volcanic activity is currently being tested in Nicaragua that uses GE Digital’s cloud-based software platform Predix. At the request of the Nicaraguan government, a team led by volcano explorer Sam Cossman is building a sensor system within the active Masaya Volcano that will be able to predict eruptions.
The overall aim is to give local residents and business owners the opportunity to prepare for moments when Masaya could erupt, but the experiment is a perfect example of how the Industrial Internet of Things is not limited to production lines or mechanical assets.
More than 80 sensors will be placed inside the crater—which is located about 13 miles from Nicaragua’s capital Managua—with the intention being to monitor the volcanic activity in real time.
“We are basically bringing the first volcano online,” said Cossman, in an interview with GE Reports.
Simulated Conditions Reveal Potential Volcanic Activity
Once the sensors are place, data scientists will be able to build digital twins that simulate the conditions within the volcano—nicknamed the “Mouth of Hell” by locals. Sensor nodes will be active both inside and around the volcano, with Cossman’s team going down about 1,200 feet into the crater in temperatures of up to 150 degrees Fahrenheit.
The sensors themselves are relatively small—around 3-inches by 4-inches—but they need to be robust enough to withstand the extreme temperatures within the volcano.
Source: Qwake via GE Reports
“We created a mesh network from more than 80 sensors,” said Cossman. “We’ll be measuring things like atmospheric pressure, temperature, various types of gasses—sulfur dioxide, hydrogen sulfide, carbon dioxide—as well as seismic data, gravity data with gravimeters and a number of other parameters in different places around and inside the volcano.”
Cossman said in the interview that there are four or five volcanic processes that can affect a human population. These include a rising body of magma, an impending explosion, degassing events that lead to gases or acid rain and eruptions that produce large volumes of ash that damage property or kill people, GE Reports said.
What Scientists And Developers Can Learn From Volcanic Data
The data gathered from the volcano will be streamed to a Predix database, which will be available to developers, residents and scientists. GE recently released the Predix Developer Kit, with almost 12,000 developers already building Industrial Internet of Things solutions using the software, according to a GE Digital press release. Developers who want to sign up for a Predix account can find more information here.
Cossman said that the team would use deep learning algorithms and artificial intelligence to discern patterns in the volcanic activity. The project is open-source and Cossman said that he hoped it would become part of a wider volcano-based initiative.
“We essentially decided to create a digital plan of the volcano. Very rarely, if ever, has someone instrumented a volcano with this many sensors, “ said Cossman. “I think it would be somewhat analogous to not feeling well and going to the doctor and having them look at one aspect of your body. It doesn’t really give you the full picture of what’s going on. To be able to look at this many parameters and then relate all those parameters to one another is really where the magic lies.”
Last image: “Volcanic Eruption,” by Flickr user Hrafnhildur Árnadóttir, Creative Commons
Like what you’ve read? Subscribe to ARC here and you’ll receive articles in your inbox daily at 4PM ET!
