Researchers from the Stanford University consider satellite images as a source to predict a poverty in the world. According to their publication in the journal Science, being combined with an artificial intelligence (AI), the imagery is able to predict areas of poverty across the globe.
A team from Stanford University decided to ‘meet’ the satellite data from the source and AI, that could analyze this data. The main aim of the scientists is a prediction of the poverty. The researchers are already able to train a computer system to highlight the impoverished areas from satellite and survey data in five African countries.
Stanford team’s point is the night lights are easy-to-understand indicators at the bottom end of the income distribution, where satellite images are dark across the board. Thus, this reliable data on local incomes in developing countries can help to hamper efforts to tackle the problem.
Co-authors of the publication are Neal Jean, Marshall Burke, they note their method could transform efforts to track and target poverty in developing countries. Dr. Burke, assistant professor of Earth system science at Stanford University explains the criteria of poverty:
“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.”
Other markers like paved roads and metal roofs (in a daylight satellite imaginary) can help distinguish different levels of economic wellbeing in developing countries, underline the Stanford scientists.