As part of our big data work, we have been looking at sources other than mobile network big data for socio-economic monitoring. Night lights images from satellites was the favorite. But I’ve been always skeptical, partly because of looking down from the New Delhi-Colombo flight which flies through the middle of India and then right down the island from Jaffna. The intensity of the lights is so much higher in southern India, than in Sri Lanka.
This story is about daytime images taken by satellites.
“If you give a computer enough data it can figure out what to look for. We trained a computer model to find things in imagery that are predictive of poverty,” said Dr Burke.
“It finds things like roads, like urban areas, like farmland, it finds waterways – those are things we recognise. It also finds things we don’t recognise. It finds patterns in imagery that to you or I don’t really look like anything… but it’s something the computer has figured out is predictive of where poor people are.”
The researchers used imagery from countries for which survey data were available to validate the computer model’s findings.
“These things [that the computer model found] are surprisingly predictive of economic livelihoods in these countries,” Dr Burke explained.