The best thing about social media is the way that it helps you to stay connected. In fact, that's probably one of the first things that comes to mind when you hear the name Facebook. But, what you might not realize is that Facebook isn't just connecting people through its website and smartphone apps. It's actually helping to connect underserved regions throughout the world.
In a recent post by Facebook's division, Connectivity Lab, more was revealed about the company's approach to solving this huge problem. "Ten percent of the world's population lives in areas of the world where connectivity is simply not available; connecting these often remote and rural areas will require the development of new wireless communication technologies and platforms."
Some of the methods revealed were, short-range access networks (like Wi-Fi hot spots), and cellular technologies for more rural regions. But, in order to determine what options work best, more information is needed.
"Creating a data set with high spatial resolution for some of the countries that could benefit from better Internet connectivity is a large undertaking," said Connectivity Lab's, Andreas Gros. "Aggregate population counts on the spatial scale of provinces or districts are known from population censuses but alone are insufficient, as these areas vary in geographical size and do not provide insight about population distributions on a granular level."
To overcome this challenge, Connectivity Lab is exploring some drastic options - including, using high-resolution satellite images to map human-made objects. This includes homes and other buildings. Connectivity Lab plans to combine the data collected from satellite mapping with the information provided by censuses to create an overall view of each area's needs.
Don't worry. Mapping these structures isn't a job for humans. That would be nearly impossible. Instead, there are high-tech computer algorithms taking on this task.
That comes with its own set of problems. According to Gros, the process is a lot like finding a needle in a haystack. "Typically, more than 99 percent of the landmass we analyze does not contain any human-made structure," Gros explained, "it therefore poses a challenge for the machine learning algorithms to learn from such an unbalanced data set."
So far, the project has analyzed 20 countries, which amounts to 21.6 million square kilometers and 350 TB of imagery.
How does this project impact all of us? Gros shared insight on that as well. "We believe this data has many more impactful applications, such as socio-economic research and risk assessment for natural disasters. We will be working with the Center for International Earth Science Information Network at Columbia University to create a combined population data set to be released later this year."