In combating poverty, like any fight, it’s good to know the locations of your targets.

That’s why Stanford scholars Marshall Burke, David Lobell and Stefano Ermon have spent the past five years leading a team of researchers to home in on an efficient way to find and track impoverished zones across Africa.

The powerful tool they’ve developed combines free, publicly accessible satellite imagery with artificial intelligence to estimate the level of poverty across African villages and changes in their development over time. By analyzing past and current data, the measurement tool could provide helpful information to organizations, government agencies and businesses that deliver services and necessities to the poor.

Details of their undertaking were unveiled in the May 22 issue of Nature Communications.

“Our big motivation is to better develop tools and technologies that allow us to make progress on really important economic issues. And progress is constrained by a lack of ability to measure outcomes,” said Burke, a faculty fellow at the Stanford Institute for Economic Policy Research (SIEPR) and an assistant professor of earth system science in the School of Earth, Energy & Environmental Sciences (Stanford Earth). “Here’s a tool that we think can help.”

Lobell, a senior fellow at SIEPR and a professor of Earth system science at Stanford Earth, says looking back is critical to identifying trends and factors to help people escape from poverty.

“Amazingly, there hasn’t really been any good way to understand how poverty is changing at a local level in Africa,” said Lobell, who is also the director of the Center on Food Security and the Environment and the William Wrigley Fellow at the Stanford Woods Institute for the Environment. “Censuses aren’t frequent enough, and door-to-door surveys rarely return to the same people. If satellites can help us reconstruct a history of poverty, it could open up a lot of room to better understand and alleviate poverty on the continent.”

The measurement tool uses satellite imagery both from the nighttime and daytime. At night, lights are an indicator of development, and during the day, images of human infrastructure such as roads, agriculture, roofing materials, housing structures and waterways, provide characteristics correlated with development.

Then the tool applies the technology of deep learning – computing algorithms that constantly train themselves to detect patterns – to create a model that analyzes the imagery data and forms an index for asset wealth, an economic component commonly used by surveyors to measure household wealth in developing nations.

The researchers tested the measuring tool’s accuracy for about 20,000 African villages that had existing asset wealth data from surveys, dating back to 2009. They found that it performed well in gauging the poverty levels of villages over different periods of time, according to their study.

Here, Burke – who is also a center fellow at the Stanford Woods Institute for the Environment and the Freeman Spogli Institute for International Studies – discusses the making of the tool and its potential to help improve the well-being of the world’s poor.

Why are you excited about this new technological resource?

For the first time, this tool demonstrates that we can measure economic progress and understand poverty interventions at both a local level and a broad scale. It works across Africa, across a lot of different years. It works pretty darn well, and it works in a lot of very different types of countries.

Can you give examples of how this new tool would be used?

If we want to understand the effectiveness of an anti-poverty program, or if an NGO wants to target a specific product to specific types of individuals, or if a business wants to understand where a market’s growing – all of those require data on economic outcomes. In many parts of the world, we just don’t have those data. Now we’re using data from across sub-Saharan Africa and training these models to take in all the data to measure for specific outcomes.

How does this new study build upon your previous work?

Our initial poverty-mapping work, published in 2016, was on five countries using one year of data. It relied on costly, high-resolution imagery at a much smaller, pilot scale. Now this work covers about two dozen countries – about half of the countries in Africa – using many more years of high-dimensional data. This provided underlying training datasets to develop the measurement models and allowed us to validate whether the models are making good poverty estimates.

We’re confident we can apply this technology and this approach to get reliable estimates for all the countries in Africa.

A key difference compared to the earlier work is now we’re using completely publicly available satellite imagery that goes back in time – and it’s free, which I think democratizes this technology. And we’re doing it at a comprehensive, massive spatial scale.

How do you use satellite imagery to get poverty estimates?

We’re building on rapid developments in the field of computer science – of deep learning – that have happened in the last five years and that have really transformed how we extract information from images. We’re not telling the machine what to look for in images; instead, we’re just telling it, “Here’s a rich place. Here is a poor place. Figure it out.”

The computer is clearly picking out urban areas, agricultural areas, roads, waterways – features in the landscape that you might think would have some predictive power in being able to separate rich areas from poor areas. The computer says, ‘I found this pattern’ and we can then assign semantic meaning to it.

These broader characteristics, examined at the village level, turn out to be highly related to the average wealth of the households in that region.

What’s next?

Now that we have these data, we want to use them to try to learn something about economic development. This tool enables us to address questions we were unable to ask a year ago because now we have local-level measurements of key economic outcomes at broad, spatial scale and over time.

We can evaluate why some places are doing better than other places. We can ask: What do patterns of growth in livelihoods look like? Is most of the variation between countries or within countries? If there’s variation within a country, that already tells us something important about the determinants of growth. It’s probably something going on locally.

I’m an economist, so those are the sorts of questions that get me excited. The technological development is not an end in itself. It’s an enabler for the social science that we want to do.

Media Contacts

Adam Gorlick, Stanford Institute for Economic Policy Research: (650) 724-0614, agorlick@stanford.edu

This article is part of the World Economic Forum Annual Meeting.

Twelve-year-old Lena is growing up poor and malnourished on Chicago’s West Side. She buys Blue Juice and Hot Chips from the corner store on her way to school. She and her classmates can afford the flavoured sugar water and salty starch, but this cheap “food” that fills up her stomach provides no nutritional value. 

Food security experts identify government support, policy implementation, private sector engagement and investment in smallholder farmers as keys to Africa’s agricultural future.

Food security experts from the Alliance for a Green Revolution in Africa (AGRA) gathered to discuss transforming food production in Africa at Stanford on Nov. 29. The symposium, hosted by the Center on Food Security and the Environment (FSE) examined the challenges, strategies, and possible solutions for catalyzing and sustaining an inclusive agriculture transformation in Africa. 

Moderator Ertharin Cousin, FSE visiting fellow and previous World Food Programme director with more than 25 years of experience on hunger, food, and resilience strategies, launched the panel by outlining Africa’s plight. “Today some 100 million of the farmers across Sub-Saharan Africa farm less than 2 hectares of land. Some 80 percent of those living in rural areas are poor. More than 30 percent of the rural population is chronically hungry and 35 percent of the under-five-year-olds are stunted. By 2050, the bulk of the world's population growth will take place on the continent. In fact, some project that 1.3 billion will be added to the continent, and Nigeria’s [population] will grow larger than the size of the United States between now and 2050,” Cousin said

.

While Africa continues to experience the highest occurrence of food insecurity worldwide, the continent also contains over 60 percent of the worlds uncultivated but fertile land. AGRA formed in 2006 to fulfill the vision that Africa can feed itself and the world. Panelists included Agnes Kalibata, AGRA President and former Minister of Agriculture and Animal Resources of Rwanda; Kanayo F. Nwanze, AGRA board member and immediate past president of the International Fund for Agricultural Development; Usha Barwale Zehr, AGRA board member and Director and Chief Technology Officer of Maharashtra Hybrid Seeds Company Private Limited; and Rajiv Shah, AGRA board member, Rockefeller Foundation President and former Administer of USAID.

Kanayo F. Nwanze stressed the importance of agricultural transformation for Africa’s future. “No country in the world ever transformed itself without going through an agrarian change. No country. Europe, 17th; Japan, 18th century; 19th century was the US, your country; China, 20th century. Why should they be different from Africa? So, first and foremost, we have to have total agricultural transformation,” Nwanze said.

AGRA president, Agnes Kalibata, also spoke to the need for policy implementation and government support in helping drive change. “AGRA as an institution can only do so much. But these governments have the potential and the capacity to reach every corner of their countries. The problem is they are challenged by capacity to do that, by capacity to design proper programs, and by capacity to implement these programs,” Kalibata said.

Expanding on governments' ability to impact and drive change, Usha Barwale Zehr highlighted Asia’s success, specifically with strategic partnerships. “…we've done a lot of talking about public/private partnership. Not so much on the ground on implementing it in a manner, which happened in Asia, for instance, where there was policy, and, most importantly, government will. The government was willing to do whatever it took to make sure that agriculture was transformed at the end of it,” Zehr said.

Beyond government and policy support the panelists also addressed the need for innovation and access to seed technologies. “Why is it that the African farmer and the Indian farmer should not have access to what the American farmer has access to today and reaps benefit from it? …So it's the hybrids, the varieties, the GM technology. Tomorrow it'll be the gene-edited products. And after that we will talk about the satellite-based imaging data that we will use for developing drought-tolerant crops for that very, very small micro environment that existed in the one district in Nigeria,” Zehr said.

"By 2050, who is going to feed Africa? … It's the youth of today. But they're not going to be using the same technologies that exist today. Just think of what IT can do, aggregation, organization of farmer's groups. So, the elements are there. I see the agriculture of tomorrow meeting the challenge – for Africa meeting that challenge is Africa being at the forefront of feeding the world. Africa has to be able to feed itself first. And we have all the opportunities there,” Nwanze said.

This is the first installment of the Global Food Security Symposium series hosted by Stanford University's Center on Food Security and the Environment and generously supported by Zach Nelson and Elizabeth Horn. FSE is a joint initiative of the Stanford Woods Institute for the Environment and the Freeman Spogli Institute for International Studies.

Stanford’s Center on Food Security and the Environment launches new symposium series focused on global food security with panel exploring Africa’s agricultural potential.

Food security experts from the Alliance for a Green Revolution in Africa (AGRA) will gather at Stanford for meetings and a symposium on transforming food production on that continent. R.S.V.P by Nov. 28 for Symposium: Can Africa rise to the challenge of feeding itself in the 21st century? | Nov. 29

Afflicted by conflict, political upheaval, and extreme weather patterns Africa continues to experience the highest occurrence of food insecurity. However, with over 60 percent of the worlds uncultivated but fertile land, there is significant room for improvement. AGRA formed in 2006 to fulfill the vision that Africa can feed itself and the world. As an alliance led by Africans with roots in farming communities across the continent, they work to understand the unique needs of farmers and offer sustainable solutions designed to boost production.

In a region with 27.4 percent of the population currently experiencing food insecurity, creating a sustainable agricultural revolution remains a key solution to improving food security across the area. Moderated by Ertharin Cousin, previous World Food Programme director, with 25 years of experience on hunger, food, and resilience strategies, the panel will explore how an agricultural transformation in Africa can sustain a growing population, relieve hunger, generate jobs, improve social cohesion, and create global exports.

Panel members include:
Ertharin Cousin (moderator), Payne Distinguished Lecturer at the Freeman Spogli Institute for International Studies and Visiting Fellow at the Center on Food Security and the Environment, former US Ambassador to the UN Agencies for Food and Agriculture in Rome.


Agnes Kalibata, the President of AGRA and former Minister of Agriculture and Animal Resources of Rwanda.

Kanayo F. Nwanze, the immediate past president of the International Fund for Agricultural Development (IFAD), winner of the Africa Food Prize in 2016, AGRA board member.

Rajiv Shah, Rockefeller Foundation President, former Administer of USAID (2010-15) where he led bipartisan reform and expansion of US efforts combating global food insecurity. During his previous work at the Gates Foundation he helped launched AGRA.

Usha Barwale Zehr, Director and Chief Technology Officer at Maharashtra – one of India’s largest and most successful multinational seed companies – and AGRA board member.

This is the first installment of the Global Food Security Symposium series hosted by Stanford University's Center on Food Security and the Environment and generously supported by Zach Nelson and Elizabeth Horn. FSE is a joint initiative of the Stanford Woods Institute for the Environment and the Freeman Spogli Institute for International Studies.