AI News, Stanford scientists combine satellite data, machine learning to map poverty

Stanford scientists combine satellite data, machine learning to map poverty

“We have a limited number of surveys conducted in scattered villages across the African continent, but otherwise we have very little local-level information on poverty,” said study co-author Marshall Burke, an assistant professor of Earth system science at Stanford and a fellow at the Center on Food Security and the Environment.

“At the same time, we collect all sorts of other data in these areas – like satellite imagery – constantly.” The researchers sought to understand whether high-resolution satellite imagery – an unconventional but readily available data source – could inform estimates of where impoverished people live.

“This makes it hard to extract useful information from the huge amount of daytime satellite imagery that’s available.” Because areas that are brighter at night are usually more developed, the solution involved combining high-resolution daytime imagery with images of Earth at night.

“And since it’s cheap and scalable – requiring only satellite images – it could be used to map poverty around the world in a very low-cost way.” Co-authors of the study, titled “Combining satellite imagery and machine learning to predict poverty”, include Michael Xie from Stanford’s Department of Computer Science and David Lobell and W.

Satellite images of Earth help us predict poverty better than ever

The newest way to accurately predict poverty comes from satellite images and machine learning.

Scientists at Stanford University fed a computer three data sources — night light images, daytime images, and actual survey data — to build an algorithm that predicts how rich or poor any given area is.

“The idea is that if we train our models right, they help us predict poverty in areas where we don’t have the surveys,” he says, “which will help out aid orgs that are working on this issue.” Using night lights to predict poverty provides important information about the economic growth of different countries, says Simon Franklin, an economics researcher at the London School of Economics who was not involved with the study.

“So if you use nighttime lights only to try to find these people, since there’s no variation in nighttime lights you can’t predict any variation in poverty.” Daytime imagery creates a fuller picture.

Building the algorithm took a two-step process called “transfer learning.” First, researchers showed a neural network daytime and nighttime images of five African countries: Uganda, Tanzania, Nigeria, Malawi, and Rwanda.

But there isn’t much survey data, so using deep learning to connect daytime images and poverty information wouldn’t create a very accurate algorithm.

If you show it two pictures of cats and one picture of a bird, it might later identify a dog as a cat because they’re about the same size and both furry with four legs.

“Dirt isn’t the same, but they learn transferable skills that they can apply to the actual task, which is competing on ice in a real bobsled.” Transfer learning is the most accurate way of predicting average household consumption and wealth of villages.

There are very rich areas and very poor areas within any given city, but it’s harder to tell the difference in urban areas by using daytime imagery alone.

But this method is cheap and easy to scale, since all the images were from the public domain, so the next step is training it to work on other countries and better map poverty across the world.

Using Machine Learning to Map Poverty from Satellite Imagery

From water levels to population density, suburban sprawl to the species of trees growing in individual forests around the world, satellite imagery can map a nearly unlimited amount of data.

By using satellite imagery the amount of work on the ground is reduced, which also reduces costs and risk factors associated with working in poverty-stricken parts of the world.

The same picture can be used for a nearly unlimited number of purposes by any organization with access to the satellite images and the ability to analyze the data contained within.

these indicators include access to water, location in comparison to an urban center and food sources, and if agriculture is viable part of the economy nearby.

People looking at thousands of images would take a long time, and people may miss some of the important big picture data when they were looking at such small images.

Fighting Poverty with Data

Speaker: Josh Blumenstock, Assistant Professor, School of Information Full Title: Fighting Poverty with Data: Research at the Intersection of Machine Learning ...

Using photos as data to understand how people live | Anna Rosling Rönnlund | TEDxStockholm

Dollar Street is a visual framework for understanding different standards of living within and between countries. By combining documentary photos and income ...

Agriculture: The Next Machine-Learning Frontier | Data Dialogs 2016

In the past decade the high-tech industry has been revolutionized by machine learning algorithms applied to everything from self-driving cars to personalized ...

Data science for the environment | Dan Hammer | TEDxBerkeley

Since the industrial revolution, as human technology has advanced, the environment has suffered. Dan Hammer is looking to turn this paradigm on its head, ...

What is poverty mapping? by Nikos Tzavidis

The historical origins of poverty research and the more recent interest in estimating poverty at disaggregated geographical levels. Although the aim is not to ...

Your brain is built for politics | Dr Darren Schreiber | TEDxLondonSalon

Combining brain imaging and political science to argue that your brain is built for politics, Dr. Schreiber found that most of his assumptions about human nature ...

Crop Yield Estimation from Satellite for Tropical Agriculture

The tropics contain some of the most important biomes for managing a variety of environmental challenges from biodiversity to climate change. But at the same ...

Using Convolutional Neural Networks to Automatically Analyze Aerial and Satellite Imagery

In this recording of our most recent Technical Staff Meeting, Lewis Fishgold walks us through the team's work on Raster Vision, a set of open source tools for ...

ICT4Eval Breakout session 7: Mapping poverty

DescriptionPresenter: • Neal Jean, Researcher, Stanford University Rapporteur: • Rogerio Bonifacio, Senior Earth Observation and Climate Analyst, Analysis ...

Predicting Poverty with Deep Learning, Neal Jean, PhD Student, Stanford at AAI16

Predicting Poverty with Deep Learning, Neal Jean, PhD Student, Stanford University at Applied AI Conference 2016 by BootstrapLabs Neal Jean, a PhD student ...