An Indian-origin scientist in the US has developed a novel technique that combines cellphone records with satellite data to create timely and incredibly detailed poverty maps, which may be useful in areas of war and conflict, as well as remote regions.
For years, policymakers have relied upon surveys and census data to track and respond to extreme poverty.
While effective, assembling this information is costly and time-consuming, and it often lacks detail that aid organisations and governments need in order to best deploy their resources.
"Despite much progress in recent decades, there are still more than one billion people worldwide lacking food, shelter and other basic human necessities," said Neeti Pokhriyal, the study's co-lead author, and a PhD candidate at the University at Buffalo in the US.
"This study details a newer mapping technique for poverty using different data sources than traditionally used," Pokhriyal told PTI.
She jointly led the study along with Damien Jacques, from Universite Catholique de Louvain, Belgium.
Some organisations define extreme poverty as a severe lack of food, health care, education and other basic needs.
Others relate it to income; for example, the World Bank says people living on less than US$ 1.25 per day (2005 prices) are extremely impoverished, researchers said.
While declining in most areas of the world, roughly 1.2 billion people still live in extreme poverty.
Most are in Asia, sub-Saharan Africa and the Caribbean.
Aid organisations and governmental agencies say that timely and accurate data are vital to ending extreme poverty.
The latest study published in the journal PNAS focused on Senegal, a sub-Saharan country with a high poverty rate.
The first data set were 11 billion calls and texts from more than nine million Senegalese mobile phone users.
All information was anonymous and it captured how, when, where and with whom people communicate with.
The second data set came from satellite imagery, geographic information systems and weather stations.
It offers insight into food security, economic activity and accessibility to services and other indicators of poverty, researchers said.
This can be gleaned from the presence of electricity, paved roads, agriculture and other signs of development.
The two datasets were combined using a machine learning- based framework. Using the framework, the researchers created maps detailing the poverty levels of 552 communities in Senegal.
Pokhriyal, who began work on the project in 2015, said the goal is not to replace census and surveys but to supplement these sources of information in between cycles.
"The study does not try to replace census. Instead, provides a way to produce inter-censal or interim statistics on poverty, that can be generated in between cycles of census," she said.
The approach could also prove useful in areas of war and conflict, as well as remote regions.
The framework also can help predict certain dimensions of poverty such as deprivations in education, standard of living and health, said Pokhriyal.
Unlike surveys or censuses, which can take years and cost millions of dollars, these maps can be generated quickly and cost-efficiently. And they can be updated as often as the data sources are updated.
Their diagnostic nature can help assist policymakers in designing better interventions to fight poverty.
