Visualizing Over A Century of World Fertility

In just 50 years, world fertility rates have been cut in half.

This sea change can be attributed to multiple factors, ranging from medical advances to greater gender equity. But generally speaking, as more women gain an education and enter the workforce, they’re delaying motherhood and often having fewer children in the process.

Today’s interactive data visualization was put together by Bo McCready, the Director of Analytics at KIPP Texas. Using numbers from Our World in Data, it depicts the changes in the world’s fertility rate—the average number of children per woman—spanning from the beginning of the 20th century to present day.

A Demographic Decline

The global fertility rate fell from 5.25 children per woman in 1900, to 2.44 children per woman in 2018. The steepest drop in this shift happened in a single decade, from 1970 to 1980.

In the interactive graphic, you’ll see graphs for 200 different countries and political entities showing their total fertility rate (FTR) over time. Here’s a quick summary of the countries with the highest and lowest FTRs, as of 2017:

At a glance, the countries with the highest fertility are all located in Africa, while several Asian countries end up in the lowest fertility list.

The notable decade of decline in average global fertility can be partially traced back to the actions of the demographic giants China and India. In the 1970s, China’s controversial “one child only” policy and India’s state-led sterilization campaigns caused sharp declines in births for both countries. Though they hold over a quarter of the world’s population today, the effects of these government decisions are still being felt.

Population Plateau, or Cliff?

The overall decline in fertility rates isn’t expected to end anytime soon, and it’s even expected to fall past 2.1 children per woman, which is known as the “replacement rate”. Any fertility below this rate signals fewer new babies than parents, leading to an eventual population decline.

Experts predict that world fertility will further drop from 2.5 to 1.9 children per woman by 2100. This means that global population growth will slow down or possibly even go negative.

Africa will continue to be the only region with significant growth—consistent with the generous fertility rates of Nigeria, the DRC, and Angola. In fact, the continent is expected to house 13 of the world’s largest megacities, as its population expands from 1.3 billion to 4.3 billion by 2100.

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.

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.

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.

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