Scientists turn to satellite images to map poverty

Scientists turn to satellite images to map poverty

Washington, Aug 19 (IANS) Locating people living in poverty, such as through door-to-door surveys, sometimes is difficult. Therefore, scientists are now turning to satellite images.

In a study published on Thursday in the US journal Science, researchers from the Stanford University used machine learning — the science of designing computer algorithms that learn from data — to extract information about poverty from high-resolution satellite imagery, Xinhua news agency reported.

They found the newly developed approach was able to “make fairly accurate predictions” of impoverished areas across five African countries: Nigeria, Tanzania, Uganda, Malawi, and Rwanda.

“Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries,” the researchers said in their paper.

According to World Bank data from 2000 to 2010, 39 out of 59 African countries conducted less than two surveys, from which nationally representative poverty measures could be constructed.

Overall, surveys are costly, infrequent, and cannot always reach countries or regions within countries, for instance, due to armed conflict.

Recent studies showed that satellite data capturing nightlights can be used to predict wealth in a given area.

However, nightlight data alone is not effective at differentiating between regions at the bottom end of the income distribution, where satellite images appear uniformly dark.

To circumvent this problem, the new study turned its attention to daylight imagery, which offers higher resolution and can capture features such as paved roads and metal roofs, markers that can help distinguish poor and ultra-poor regions.

The researchers then developed a sophisticated learning algorithm that categorizes these features and found that this method did a surprisingly good job predicting the distribution of poverty.

Compared with nightlight models, the new model was 81 per cent more accurate in predicting poverty in regions under the poverty line, and 99 per cent more accurate in areas that are two times below the poverty line.

“We demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high- resolution satellite imagery,” the study said.

“It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.”

Leave a Reply

Please enter your comment!

The opinions, views, and thoughts expressed by the readers and those providing comments are theirs alone and do not reflect the opinions of www.mangalorean.com or any employee thereof. www.mangalorean.com is not responsible for the accuracy of any of the information supplied by the readers. Responsibility for the content of comments belongs to the commenter alone.  

We request the readers to refrain from posting defamatory, inflammatory comments and not indulge in personal attacks. However, it is obligatory on the part of www.mangalorean.com to provide the IP address and other details of senders of such comments to the concerned authorities upon their request.

Hence we request all our readers to help us to delete comments that do not follow these guidelines by informing us at  info@mangalorean.com. Lets work together to keep the comments clean and worthful, thereby make a difference in the community.

Please enter your name here