Researchers have merged satellite imagery and AI for the prediction of regions facing poverty worldwide. In the developing countries, there is less reliable data about local incomes, which hinders efforts to deal with the problem.

A Stanford University team hasmanaged to guide a computer system to spot poor regions from satellite and survey data in five African nations. The findings have got published in the journal Science.

According to Neal Jean, Marshall Burke and colleagues, the technique can possibly bring a transformation in the efforts to track and focus at poverty in such nations.

While speaking to BBC's Science in Action programme, Dr Burke, assistant professor of Earth system science at Stanford, said that the World Bank, poverty data keeper, for so long has considered a person poor if he lives on less than $1 per day.

Dr Burke added, “We traditionally collect poverty data through household surveys... we send survey enumerators around to houses and we ask lots of questions about income, consumption—what they've bought in the last year - and we use that data to construct our poverty measures”.

The surveys are irregular, expensive and at times impossible to conduct in specific areas of nations because of, for instance, armed conflict. This there is a lot of need for other precise measures of household intake and income in the budding world.

The thought of mapping poverty using satellite imagery isn’t entirely fresh. Studies in the past have demonstrated that space-based data that record night lights can be used for making wealth prediction in a specific area.

But night lights aren’t such a good indicator when it comes to income distribution where satellite pictures are dark throughout the board.

A report published in BBC informed, "There's little reliable data on local incomes in developing countries, which hampers efforts to tackle the problem. A team from Stanford University were able to train a computer system to identify impoverished areas from satellite and survey data in five African countries."

"The World Bank, which keeps the poverty data, has for a long time considered anyone who is poor to be someone who lives on below $1 a day," Dr Burke, assistant professor of Earth system science at Stanford, told the BBC's Science in Action programme.

So there is a need for other accurate measures of household consumption and income in the developing world. The idea of mapping poverty from satellite imagery is not completely new. Recent studies have shown that space-based data that capture night lights can be used to predict wealth in a given area.

According to a report in Engadget by Andrew Dalton, "A new study in the journal Science shows how a combination of satellite imagery and machine learning algorithms can be used to predict poverty in regions of the world where data is otherwise unavailable."

Step two added in economic survey data which, while incomplete for the majority of the region, added much needed context and granularity. The system could already recognize a village, for instance, but the survey data could tell it the household income of that village.

That said, the system still has its limitations. While it may be useful for finding income differences between rural and urban areas, it's not so good at finding those minute differences within one dense urban center. At the moment, the algorithm only works in the five African countries where it was tested, but because all the data is publicly available it's just a matter of training the system to look at other parts of the world.