Satellite images can help predict poverty stricken areas

Satellite imagery in combination with machine learning algorithms can be used to determine poverty levels in the regions where data is otherwise unavailable, says a new study in the journal Science.

Nighttime lighting which has long been used to predict a region's wealth often proves ineffective when one takes into consideration areas which have no power at all. To fix this, this new model, uses both nighttime images as well as publicly available daytime imagery and survey data to teach a computer system to estimate just how rich or poor an area is, says lead author Neal Jean, a doctoral candidate studying machine learning at Stanford.

Jean and his team created their algorithm in two steps. They first ran day and night satellite images of Uganda, Tanzania, Nigeria, Malawi, and Rwanda through a neural network, which would find the villages and cities and try to predict where the lights would be at night. If there are houses in a region, for example, the system would predict that area would be lit up at night.

In the next stage they added in economic survey data which, though 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. When the system identified a similar village nearby – one which had no survey data available – it could start to create an estimate for the household income in that village.

The paper says that this two-step model creates a truer picture of wealth in a region than the night lights model anywhere from 81 to 99 percent of the time.

The model however isn’t foolproof. Though it may appear useful for finding income differences between rural and urban areas, it might not be as effective in finding those minute differences within one dense urban center.There are very rich areas and very poor areas within any given city, but it’s harder to tell the difference in urban areas by using daytime imagery alone.

Also, Alexei Abrahams, an economist at the University of California-San Diego, pointed out that the current study uses an old series of night light images. Since 2012, NASA has been recording night lights with a new and more accurate satellite, so further studies should use the better data. At the moment, though 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.