Poverty, along with its health and social impacts, is a monumental and widespread issue, but collecting solid data on the world's impoverished zones is anything but straightforward. Modern technology, however, is affording researchers exciting new ways to bring these areas into focus, the latest example being a mix of smartphone and satellite data used to create a high-resolution map of poverty distribution across Bangladesh.
Researchers already have a handle on the poverty-stricken regions of the world, but current approaches have serious limitations. Data is collected through on-the-ground surveys, a method that is expensive, time-consuming and only offers limited information.
"Census and household surveys are normally used as data sources to estimate rates of poverty," explains Dr Jessica Steele from the University of Southampton and lead author on the new study. "However, they aren't regularly updated – for example, censuses only take place every ten years – and in low income countries, surveys can be patchy."
Back in August, researchers at Stanford University made a promising breakthrough in this area. They came up with a machine learning algorithm that could be fed satellite imagery highlighting brighter areas and features associated with economic development, such as road and urban areas, to accurately predict the wealth of a region.
The new technique, developed by the University of Southampton, the Flowminder Foundation, Telenor Research and mobile phone company Grameenphone, does have some similarities. They used remote sensing from satellites to gauge the living conditions of remote communities. This included their distance to roads and cities, whether they can light their homes, and also an assessment on agricultural productivity based on rainfall, vegetation and temperature data.
But where the new approach really takes things to another level is by bringing mobile phone data into the mix. This allowed the researchers to gain an approximate location of where users are situated, their data and credit usage, how many texts they are sending and the times and durations of calls. Furthermore, it can indicate how far users are traveling, the proportion of users in a single area and whether they are using a basic phone device or a smartphone.
"The advantage of using mobile phone data is that it provides us with information which is continually updated, can be interrogated in a variety of ways and can track changes on an ongoing basis," says Steele. "Paired with satellite data that has similar features, it can give a much more dynamic view of poverty and its geographic spread."
From here, the team hopes to apply this approach to other countries, providing governments and relief organizations with a more detailed, accurate and timely way to track poverty across the globe.
The research was published in the Journal of The Royal Society Interface.
Source: University of Southampton via Phys.org
Poverty, along with its health and social impacts, is a monumental and widespread issue, but collecting solid data on the world's impoverished zones is anything but straightforward. Modern technology, however, is affording researchers exciting new ways to bring these areas into focus, the latest example being a mix of smartphone and satellite data used to create a high-resolution map of poverty distribution across Bangladesh.
Researchers already have a handle on the poverty-stricken regions of the world, but current approaches have serious limitations. Data is collected through on-the-ground surveys, a method that is expensive, time-consuming and only offers limited information.
"Census and household surveys are normally used as data sources to estimate rates of poverty," explains Dr Jessica Steele from the University of Southampton and lead author on the new study. "However, they aren't regularly updated – for example, censuses only take place every ten years – and in low income countries, surveys can be patchy."
Back in August, researchers at Stanford University made a promising breakthrough in this area. They came up with a machine learning algorithm that could be fed satellite imagery highlighting brighter areas and features associated with economic development, such as road and urban areas, to accurately predict the wealth of a region.
The new technique, developed by the University of Southampton, the Flowminder Foundation, Telenor Research and mobile phone company Grameenphone, does have some similarities. They used remote sensing from satellites to gauge the living conditions of remote communities. This included their distance to roads and cities, whether they can light their homes, and also an assessment on agricultural productivity based on rainfall, vegetation and temperature data.
But where the new approach really takes things to another level is by bringing mobile phone data into the mix. This allowed the researchers to gain an approximate location of where users are situated, their data and credit usage, how many texts they are sending and the times and durations of calls. Furthermore, it can indicate how far users are traveling, the proportion of users in a single area and whether they are using a basic phone device or a smartphone.
"The advantage of using mobile phone data is that it provides us with information which is continually updated, can be interrogated in a variety of ways and can track changes on an ongoing basis," says Steele. "Paired with satellite data that has similar features, it can give a much more dynamic view of poverty and its geographic spread."
From here, the team hopes to apply this approach to other countries, providing governments and relief organizations with a more detailed, accurate and timely way to track poverty across the globe.
The research was published in the Journal of The Royal Society Interface.
Source: University of Southampton via Phys.org
