Facebook is Using AI To Map Population Density Around the World (theverge.com) 31
Facebook has always been a company with global ambition, but few projects illustrate this better than its ongoing attempt to map the world's population density using AI. From a report: The company first unveiled this work back in 2016 when it created maps for 22 nations. Today, it expanded that with new maps that cover the "majority" of Africa. "The project will eventually map nearly the whole world's population," Facebook said in a blog post. As Facebook explains, creating maps like this is a challenging job for humans. Although we have high-resolution satellite imagery that covers pretty much every corner of the globe, turning this into useful information is a time-consuming process. To create population density maps, for example, humans have to label each building in the images, then cross-reference this with census data.
This is particularly tricky in the African continent where census tracts can cover regions as large as 150,000 square miles but contain just 55,000 people. Luckily, this sort of task -- tedious but simple -- is perfect for AI. To automate this process, Facebook's engineers used data from open-source mapping project Open Street Map to train a computer vision system that can recognize buildings in satellite imagery. They then used this to remove the vast majority of the satellite data that showed unoccupied land.
This is particularly tricky in the African continent where census tracts can cover regions as large as 150,000 square miles but contain just 55,000 people. Luckily, this sort of task -- tedious but simple -- is perfect for AI. To automate this process, Facebook's engineers used data from open-source mapping project Open Street Map to train a computer vision system that can recognize buildings in satellite imagery. They then used this to remove the vast majority of the satellite data that showed unoccupied land.
Facebook? (Score:2)
Interesting, and it will be quite valuable to actually have this map-- we all pretty much can guess where the population lives, but guessing isn't the same as data.
But... Facebook? Why facebook?
I'm guessing that this is part of their initiative to take over the world by making Facebook the default internet connection for people who aren't currently internet connected.
Re: (Score:2)
Of course they want to know where more people are that don't have Facebook yet.
Re: (Score:3)
Why facebook?
Data is their business. Presumably they have the raw data necessary to come up with this map, maybe they will even publish it as a freebie, but for them it'll probably just be a little exercise in machine learning, to see what else they can glean from the piles of other data they have. Maybe map this population data to affluence, sexual preference, age, political leaning, spending patterns... and that good stuff they can sell.
Re: (Score:3)
Re: Facebook? (Score:2)
You could use the fb map vs actual census numbers and find where the percentage of people on Facebook is lowest and move there
Re: (Score:2)
Why facebook?
Remember who Facebook works for. (Advertisers if you forgot.)
Population density or building density? (Score:3)
Re: (Score:2)
there are so many exceptions...that the results would be next to useless.
Not at all; they can compare areas with known populations to areas with unknown. The estimate won't be exact, but it will be close enough to make informed decisions such as whether there are enough people to invest in some infrastructure.
Re: (Score:2)
While buildings certainly imply human habitation, there are so many exceptions (farming/retail/industrial/utility buildings, abandoned homes, seasonal homes, homeless people, nomads, migrants, refuges, homes with more or less occupants than average [and how do you determine average])
And that's why they use AI, of course. You don't just count buildings, you count and classify types of building, and then use the results of the type of building to estimate the number of people, based on the knowledge gained from other areas where you can correlate the type of building with the number of people.
Your AI is going to have to know ok, this building is for farming, here are the homes for the farmers, that one over there is a utility building, that other one a barn; we see five tractors and thre
AI is a solution looking for a problem (Score:1)
And secondly it isn't even real "AI."
They changed the definition of AI to be the same as "Machine Learning" and "AI" as most people knew it is now known as "AGI"
It's a marketing ploy.
Re: (Score:2)
I know the notion of "artificial intelligence" can really get stretched but this seems like they're conflating AI with "anyting on a computer". Definitely you want computers doing this (because of the volume of data), but aside from a little bit of classifying building types or land use there isn't much more than simple counting involved.
Ob (Score:2)
1600 Pennsylvania Ave, Washington DC.
Very dense. The best density.
Re: Ob (Score:1)