post

ZONE SE7EN > Blog > Storage > Big Data Analytics is Helping in the Search for Missing Flight 370

Big Data Analytics is Helping in the Search for Missing Flight 370

  • By Allie Philpin 
  • Category: Storage 
  • Comments (0) 

By Allie Philpin

As concern continues to grow over missing Malaysia Airlines Flight 370 that suddenly, mysteriously disappeared in South East Asia, the number of people joining the search grows and they are using every tool they can to help them, the latest of which is Big Data analytics.

Adaptive Computing’s Chief Architect, Daniel Hardman, has become a ‘supervisor’ in the search as their Moab data analytics platform, used by a range of global organisations including the University of Cambridge, Oak Ridge National Laboratory and The Weather Channel, is being used to aid the search.  Their Moab HPC Suite and Cloud Suite, integral elements of their Big Workflow data centre package, is able to unify all resources from data centres and optimises the analysis process by streamlining workflows to provide insights into the big data across multiple platforms, locations and environments.

DigitalGlobe are another company involved in the search; commercial vendors of geospatial content and space imagery, is using their crowdsourcing website, Tomnod, to encourage the public to join in the search for the airliner.  Together with Adaptive Computing, they are running a crowdsourcing-style search for Flight 370, and anyone can join in via this website.

Focusing the search on oceans around Malaysia, DigitalGlobe uses its satellites to take hundreds of photographs that are then transmitted to their Big Data storage banks.  From there, any corrections are made, such as contrast and colour consistency, as well as finding and deleting photographs that are unusable, including those where cloud hides the view.  Utilising Adaptive Computing’s Big Workflow with Moab solution, resources can be allocated so that data throughput is maximised, and the system is continually monitored to ensure efficiency.  With 4.5 billion square kilometres of global coverage already in their archives, it made sense to use the Tomnod crowdsourcing platform to engage the help of the general public in using the satellite imagery to try and find missing Flight 370.

Jill King, a spokeswoman for Adaptive Computing, explained: “They will create a custom algorithm that says: ‘Here’s what a whole plane looks like; here’s what possible pieces and parts look like.’  They are training their computers to look for those types of shapes.  It can also look for certain colours – even certain types of reflective light.  The data centre then will use Moab to analyse each of those shapes to see if they’re a match to Flight 370.”

In this unusual, distressing case of the missing Malaysian Flight 370, DigitalGlobe has gathered great quantities of human-created data through the crowdsourcing platform.  Hardman explains: “On Tomnod.com, any person can go and just look at photos in the grid, and you’re supposed to flag anything that looks interesting.  The problem is, humans can see lots of things, but they might not always be the right things.  So, what DigitalGlobe does is get the input of many thousands of people, run it through Big Data filters on the back end; they then do a cluster analysis on that.  Then, experts in search-and-rescue may say, ‘There’s a hot spot, go fly over this.’”

As I write this, the search continues, only now with thousands of eyes from the general public helping, and the use of an extremely high-powered photo and data analytics solution.

Subscribe to our mailing list

* indicates required Email Address * First Name * Last Name *