Connect with us

Technology

How Facebook is Using Machine Learning to Map the World Population

Published

on

When it comes to knowing where humans around the world actually live, resources come in varying degrees of accuracy and sophistication.

Heavily urbanized and mature economies generally produce a wealth of up-to-date information on population density and granular demographic data. In rural Africa or fast-growing regions in the developing world, tracking methods cannot always keep up, or in some cases may be non-existent.

This is where new maps, produced by researchers at Facebook, come in. Building upon CIESIN’s Gridded Population of the World project, Facebook is using machine learning models on high-resolution satellite imagery to paint a definitive picture of human settlement around the world. Let’s zoom in.

Connecting the Dots

Will all other details stripped away, human settlement can form some interesting patterns. One of the most compelling examples is Egypt, where 95% of the population lives along the Nile River. Below, we can clearly see where people live, and where they don’t.

View the full-resolution version of this map.

facebook population density egypt map

While it is possible to use a tool like Google Earth to view nearly any location on the globe, the problem is analyzing the imagery at scale. This is where machine learning comes into play.

Finding the People in the Petabytes

High-resolution imagery of the entire globe takes up about 1.5 petabytes of storage, making the task of classifying the data extremely daunting. It’s only very recently that technology was up to the task of correctly identifying buildings within all those images.

To get the results we see today, researchers used process of elimination to discard locations that couldn’t contain a building, then ranked them based on the likelihood they could contain a building.

process of elimination map

Facebook identified structures at scale using a process called weakly supervised learning. After training the model using large batches of photos, then checking over the results, Facebook was able to reach a 99.6% labeling accuracy for positive examples.

Why it Matters

An accurate picture of where people live can be a matter of life and death.

For humanitarian agencies working in Africa, effectively distributing aid or vaccinating populations is still a challenge due to the lack of reliable maps and population density information. Researchers hope that these detailed maps will be used to save lives and improve living conditions in developing regions.

For example, Malawi is one of the world’s least urbanized countries, so finding its 19 million citizens is no easy task for people doing humanitarian work there. These maps clearly show where people live and allow organizations to create accurate population density estimates for specific areas.

rural malawi population pattern map

Visit the project page for a full explanation and to access the full database of country maps.

Subscribe to Visual Capitalist
Click for Comments

AI

Visualizing the Top U.S. States for AI Jobs

Nearly 800,000 AI jobs were posted in the U.S. throughout 2022. View this graphic to see a breakdown by state.

Published

on

Visualizing the Top U.S. States for AI Jobs

Much ink has been spilled over fears that artificial intelligence (AI) will eliminate jobs in the economy. While some of those fears may be well-founded, red-hot interest in AI innovation is creating new jobs as well.

This graphic visualizes data from Lightcast, a labor market analytics firm, which shows how many AI-related jobs were posted in each state throughout 2022.

In total there were 795,624 AI jobs posted throughout the year, of which 469,925 (59%) were in the top 10. The full tally is included in the table below.

RankStateNumber of job postings% of total
1California142,15417.9%
2Texas66,6248.4%
3New York43,8995.5%
4Massachusetts34,6034.3%
5Virginia34,2214.3%
6Florida33,5854.2%
7Illinois31,5694.0%
8Washington31,2843.9%
9Georgia26,6203.3%
10Michigan25,3663.2%
11North Carolina23,8543.0%
12New Jersey23,4472.9%
13Colorado20,4212.6%
14Pennsylvania20,3972.6%
15Arizona19,5142.5%
16Ohio19,2082.4%
17Maryland16,7692.1%
18Minnesota11,8081.5%
19Tennessee11,1731.4%
20Missouri10,9901.4%
21Oregon10,8111.4%
22Washington, D.C.9,6061.2%
23Indiana9,2471.2%
24Connecticut8,9601.1%
25Wisconsin8,8791.1%
26Alabama7,8661.0%
27Kansas7,6831.0%
28Arkansas7,2470.9%
29Utah6,8850.9%
30Nevada6,8130.9%
31Idaho6,1090.8%
32Oklahoma5,7190.7%
33Iowa5,6700.7%
34South Carolina4,9280.6%
35Louisiana4,8060.6%
36Kentucky4,5360.6%
37Nebraska4,0320.5%
38Delaware3,5030.4%
39New Mexico3,3570.4%
40Rhode Island2,9650.4%
41New Hampshire2,7190.3%
42Hawaii2,5500.3%
43Mississippi2,5480.3%
44Maine2,2270.3%
45South Dakota2,1950.3%
46Vermont1,5710.2%
47North Dakota1,2270.2%
48Alaska9700.1%
49West Virginia8870.1%
50Montana8330.1%
51Wyoming7690.1%

The following chart adds some context to these numbers. It shows how the percentage of AI job postings in some of the top states has changed since 2010.

We can see that California quickly became the primary destination for AI jobs in the early 2010s, presumably as Silicon Valley companies began developing the technology.

California’s share has since declined, with a significant number of jobs seemingly moving to Texas. In fact, many tech companies are relocating to Texas to avoid California’s relatively higher taxes and cost of living.

The 10 Most In-Demand Specialized Skills

Lightcast also captured the top 10 specialized skills that were required for AI-related jobs. These are listed in the table below.

SkillFrequency (number of postings)Frequency (% of postings)
Python296,66237%
Computer Science260,33333%
SQL185,80723%
Data Analysis159,80120%
Data Science157,85520%
Amazon Web Services155,61519%
Agile Methodology152,96519%
Automation138,79117%
Java133,85617%
Software Engineering133,28617%

If you’re interested in a career that focuses on AI, becoming proficient in Python is likely to be a good first step.

Continue Reading

Subscribe

Popular