The model can provide the data policymakers need when they decide where to implement their economic development programs.
The model can provide the data policymakers need when they decide where to implement their economic development programs.

Scientists Can Track Poverty From Satellites

Scientists Can Track Poverty From Satellites

You can get a pretty good idea of a country’s wealth by seeing how much it shines at night.
However, nighttime lights don’t tell you which neighborhoods or villages within a large region are merely poor and which are home to people living in abject poverty. That’s the level of detail policymakers need when they decide where to implement their economic development programs.
Researchers at Stanford University, USA, came up with a new way to get computers and satellites to get this detail.
According to The Bulletin, their computer model’s predictive power is at least as good as methods that rely on data from outdated surveys.
The Stanford approach requires a few key ingredients. Some kind of data that covers every single place where people live, a smaller amount of data that you know is pretty accurate and a powerful computer that can calibrate the trove of “noisy” data to the smaller amount of reliable data.
The researchers tested their system with five African countries: Nigeria, Tanzania, Uganda, Malawi and Rwanda and started with nighttime images. Places that were brighter at night were presumed to be more economically developed than places that were dim.
Then they had their computer program compare the nighttime images to higher-resolution daytime images available via Google Static Maps. The program was able to recognize certain shapes in the daytime pictures that were correlated with economic development.
“Without being told what to look for, our machine learning algorithm learned to pick out of the imagery many things that are easily recognizable to humans—things like roads, urban areas and farmland,” study lead author Neal Jean, a computer science graduate student at Stanford’s School of Engineering, said in a statement.
Other recognizable features included waterways and buildings. The computer even learned to distinguish metal rooftops from those made of grass, thatch or mud, according to the study.
The Stanford team used statistical methods to determine how the presence (or absence) of items identified in the daytime pictures related to income data collected in surveys. The type of roofing material on a building was directly related to income, for instance. So was a location’s distance from an urban area.
Jean and his colleagues aren’t the only ones excited about the prospect of using satellites and computers to fight poverty.
In an essay that accompanies the study, Joshua Blumenstock of UC Berkeley’s Data Science and Analytics Lab said that making use of daytime satellite data, which contains far more information than nighttime images, can “make it possible to differentiate between poor and ultra-poor regions.” This can help ensure that resources get to those with the greatest need.


Short URL : http://goo.gl/LAsgDE
  1. http://goo.gl/lVnX4Z
  • http://goo.gl/399wqN
  • http://goo.gl/DspWKL
  • http://goo.gl/1cxCsi
  • http://goo.gl/ZE8ST5

You can also read ...

CBI Outlines Top Priorities
The governor of the Central Bank of Iran, who took the reins...
Non-Oil Trade Value With Egypt Tops 80%
Iran traded 298,616 tons of non-oil commodities worth $128.23...
Colza Production Breaks 30-Year Record
Colza production in Iran since the beginning of the current...
Interest Rate Growth Gathers Pace
Two major banks have been allowed by the Central Bank of Iran...
IKCO to Deliver Presold Peugeot 2008 SUVs
Extending apologies for the prolonged delay in the delivery of...
Domestic Shoe Industry Hit by Raw Material Shortage
Domestic shoe production has declined by over 70%, the head of...
Vacuum Cleaners Imported From 14 Countries
More than $29 million worth of vacuum cleaners were imported...
Rail Exports From Qom to CIS Grow 29%
More than 3,403 tons of goods were exported via railroads from...