This Global Food Security Strategy presents an integrated whole-of-government strategy and agency-specific implementation plans as required by the Global Food Security Act of 2016 (GFSA).
"Right now, the world is closer than ever before to ending global hunger, undernutrition, and extreme poverty, but significant challenges and opportunities remain, including urbanization, gender inequality, instability and conflict, the effects of a changing climate, and environmental degradation. Despite our collective progress in global food security and nutrition over recent years, a projected 702 million people still live in extreme poverty, nearly 800 million people around the world are chronically undernourished, and 159 million children under five are stunted. Food security is not just an economic and humanitarian issue; it is also a matter of security, as growing concentrations of poverty and hunger leave countries and communities vulnerable to increased instability, conflict, and violence." From the USAID Oct. 3 release.
You can read more and download the pdf of the Global Food Security Strategy at the USAID website.
Policy-makers in the world's poorest countries are often forced to make decisions based on limited data. Consider Angola, which recently conducted its first postcolonial census. In the 44 years that elapsed between the prior census and the recent one, the country's population grew from 5.6 million to 24.3 million, and the country experienced a protracted civil war that displaced millions of citizens. In situations where reliable survey data are missing or out of date, a novel line of research offers promising alternatives. On page 790 of this issue, Jean et al.(1) apply recent advances in machine learning to high-resolution satellite imagery to accurately measure regional poverty in Africa.
The availability of accurate and reliable information on the location of impoverished zones is surprisingly lacking for much of the world. Applying machine learning to satellite images could identify impoverished regions in Africa.
One of the biggest challenges in providing relief to people living in poverty is locating them. The availability of accurate and reliable information on the location of impoverished zones is surprisingly lacking for much of the world, particularly on the African continent. Aid groups and other international organizations often fill in the gaps with door-to-door surveys, but these can be expensive and time-consuming to conduct.
Image
In the current issue of Science, Stanford researchers propose an accurate way to identify poverty in areas previously void of valuable survey information. The researchers used machine learning – the science of designing computer algorithms that learn from data – to extract information about poverty from high-resolution satellite imagery. In this case, the researchers built on earlier machine learning methods to find impoverished areas across five African countries.
“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 coauthor 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. The difficulty was that while standard machine learning approaches work best when they can access vast amounts of data, in this case there was little data on poverty to start with.
“There are few places in the world where we can tell the computer with certainty whether the people living there are rich or poor,” said study lead author Neal Jean, a doctoral student in computer science at Stanford’s School of Engineering. “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 the Earth at night. The researchers used the “nightlight” data to identify features in the higher-resolution daytime imagery that are correlated with economic development.
“Without being told what to look for, our machine learning algorithm learned to pick out of the imagery many things that are easily recognizable to humans – things like roads, urban areas and farmland,” said Jean. The researchers then used these features from the daytime imagery to predict village-level wealth, as measured in the available survey data.
They found that this method did a surprisingly good job predicting the distribution of poverty, outperforming existing approaches. These improved poverty maps could help aid organizations and policymakers distribute funds more efficiently and enact and evaluate policies more effectively.
“Our paper demonstrates the power of machine learning in this context,” said study co-author Stefano Ermon, assistant professor of computer science and a fellow by courtesy at the Stanford Woods Institute of the Environment. “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. Matthew Davis from Stanford's School of Earth, Energy and Environmental Sciences and the Center on Food Security and the Environment. For more information, visit the research group's website at: http://sustain.stanford.edu/
Stanford pediatrician Paul Wise stooped below the black tarp roof of a cinderblock house in Guatemala to offer his condolences to a mother who had just lost her child.
“Doctor Pablo,” as he is known in the communities around San Lucas Tolimán, talked softly as he relayed his sympathies to the mother, whose 9-year-old son had been a patient of his.
Stanford’s Children in Crisis Initiative seeks to save the lives of children in areas of poor governance. In Guatemala, their efforts work toward eliminating death by malnutrition for children under 5.
The boy’s genetic disorder would have been terminal anywhere, but thanks to Wise and local health promoters, the boy’s family had years with him instead of months.
While Wise spoke to the heartbroken mother, his Stanford research assistant Alejandro Chavez helped the promoters set up inside a local community center to measure the weight and height of local kids to determine their nutrition level.
Chavez and the promoters had worked together for months to create an app for tablets that will make it easier to find malnourished children.
The app they designed will decrease training time for new health promoters and allow the program to expand. The goal is to distribute the app globally to help programs in other countries tackle malnutrition.
Children in crisis
As recently as 2005, about one of every 20 children in this rural area of Guatemala died before their 5th birthday. Almost half the deaths were associated with severe malnutrition.
“The death of any child is always a tragedy, but the death of any child from preventable causes is always unjust,” said Wise, a Stanford Health Policy core faculty member.
Along with other faculty from the Freeman Spogli Institute for International Studies (FSI) and the School of Medicine, Wise created the Children in Crisis Initiative to save the lives of children in areas of poor governance. The program brings together Stanford researchers and students across disciplines.
Nowhere are their efforts better illustrated than in the rural communities around San Lucas Tolimán, in the central mountains of Guatemala.
The program’s effectiveness rests on a deep respect for the local communities merged with innovation by Stanford researchers.
“It’s absolutely essential to any program that the people in need be part of the solution,” said Wise. Unlike many nongovernmental organizations and health programs, Wise believes the way to create a sustainable health system is for the locals to run it, so the health promoters manage the program’s day-to-day activities.
Image
This leaves the Stanford team free to focus on innovation – such as the new app. They believe the technology could change child health programs around the world. Wise’s team has partnered with Medic Mobile – a nonprofit that creates open-source software for health care workers – which plans to distribute the app to other areas suffering from malnutrition.
The six Android tablets purchased by Children in Crisis are enough to monitor the program’s 1,500 kids through the app.
Role of nutrition
When done well, nutrition surveillance is very effective at decreasing child mortality in poor countries.
“Nutrition contributes enormously to health and well-being,” Wise said as he walked through Tierra Santa, a small community near San Lucas, making house calls. “So the focus of our work turned to improving young child nutrition. It’s not an easy thing to do in a place that’s extremely poor.”
Wise and his colleagues – Stanford medical student Tori Bawel and Stanford professor of pediatrics Lisa Chamberlain – made their rounds during their visit in March. Evidence of poverty was everywhere.
Here, clean tap water is a dream and even the sturdier homes often lack four walls or paned windows, though the children were neatly dressed in T-shirts or colorful traje, traditional Mayan clothing.
It’s hard to provide proper nutrition when most families can’t find enough work to buy adequate food. But a little help can make a big difference.
Bawel, a first-year medical student who plans a career improving health in areas of poverty, was struck by the impact the promoter program has had on the community.
“There are children who need supplements and nutrition to stay alive,” she said. “Without this program, that infrastructure does not exist.”
With FSI’s assistance, the nutrition program distributes Incaparina, a supplement of cornmeal, soy and essential nutrients. The sweet, mealy drink helps the program’s most malnourished children get back on track.
Image
Every two months, the promoters gather each community’s children to measure their weight and height. Children and their mothers sit patiently, waiting for their turn. The children enjoy a cup of Incaparina, and their mothers eagerly listen to the promoters’ tips for keeping their children healthy.
“It’s very important to me,” said Elsira Rosibel Samayoa, who brought her 2-year-old to be measured. “There are mothers who don’t understand the importance of monitoring their children’s weight, but I do.”
Since its implementation in 2009, the Stanford program has slashed nutrition-based mortality in the participating communities by about 80 percent and decreased severe malnutrition by more than 60 percent – saving hundreds of children’s lives.
However, nutrition surveillance and intervention isn’t easy. Tracking nutrition takes training and expertise, and when the local population rarely exceeds a fourth-grade education, learning these skills is especially challenging. Detailed graphs on a standard growth chart are essential to identifying malnourished children.
“The community health workers are extremely capable and smart, but some have never seen a graph before,” said Wise. “Think about what it is to try to explain a graph to someone for the first time.”
It takes the health workers about three years to learn to graph and then interpret the results for intervention.
Wise said, “So we all got together and said, ‘How do we make this easier to do?’”
The app was the answer.
‘Let’s create an app’
Enter Alejandro Chavez, a recent Stanford computer science graduate and Stanford Health Policy research assistant. He developed the app to collect child health data, then determine the child’s degree of malnutrition and suggest intervention.
“The major goal was to lower training requirements and make programs like this simpler to start and maintain,” said Chavez, who now lives and works in Guatemala, where he gets daily feedback from the health promoters.
“I feel like they’ve been very honest with me about things I need to improve,” he said.
Cesia Lizeth Castro Chutá is a senior coordinator for the program who has worked with Chavez to ensure that the app meets the promoters’ needs.
“The tablet automatically generates the information we need to know,” she said. “It becomes easier to confirm that a child is malnourished and needs supplements.”
Looking forward
Image
With the app’s launch, it looks like training time for the promoters will be reduced from three years to less than six months. That means new communities can be incorporated into the program quickly, creating broader access to care.
Meanwhile, many health programs around the world are waiting to see how well the Stanford app works in Guatemala.
Josh Nesbit, a Stanford alumnus and Medic Mobile CEO, said, “As more health programs recognize the importance of nutrition and implement community-based interventions, screening and surveillance tools will be critical. We must learn from Dr. Wise’s success.”
Join us for a free screening of "Seeds of Time: One man's journey to save the future of our food" from Academy Award nominated director Sandy McLeod.
Synposis:
A perfect storm is brewing as agriculture pioneer Cary Fowler races against time to protect the future of our food. Seed banks around the world are crumbling, crop failures are producing starvation and rioting, and the accelerating effects of climate change are affecting farmers globally. Communities of indigenous Peruvian farmers are already suffering those effects, as they try desperately to save over 1,500 varieties of native potato in their fields. But with little time to waste, both Fowler and the farmers embark on passionate and personal journeys that may save the one resource we cannot live without: our seeds.
Dr. Fowler is at Stanford as a visiting scholar with FSE and will introduce the film, then answer questions following the screening.
In 2007, "solar market gardens" were installed in 2 villages for women’s agricultural groups as a strategy for enhancing food and nutrition security. Data were collected through interviews at installation and 1 year later from all women’s group households (30–35 women/group) and from a random representative sample of 30 households in each village, for both treatment and matched-pair comparison villages. Comparison of baseline and endline data indicated increases in the variety of fruits and vegetables produced and consumed by SMG women’s groups compared to other groups. The proportion of SMG women’s group households engaged in vegetable and fruit production significantly increased by 26% and 55%, respectively (P < .05). After controlling for baseline values, SMG women’s groups were 3 times more likely to increase their fruit and vegetable consumption compared with comparison non-women’s groups (P < .05). In addition, the percentage change in corn, sorghum, beans, oil, rice and fish purchased was significantly greater in the SMG women’s groups compared to other groups. At endline, 57% of the women used their additional income on food, 54% on health care, and 25% on education. Solar Market Gardens have the potential to improve household nutritional status through direct consumption and increased income to make economic decisions.
David Lobell’s recent research indicates that negative impacts to the global agriculture system are much more likely, more severe and wider-ranging in the face of human-caused climate change. Temperature increases are the main drier behind these far-reaching impacts.. There are several pathways toward adaptation, though none of them appears to completely offset the losses. Research highlighted in this brief offers insights for institutions and decisionmakers concerned with protecting food security and international stability throughout the coming decades.
Sam Heft-Neal is a research fellow at the Center on Food Security and the Environment and in the Department of Earth System Science. Sam is working with Marshall Burke to identify the impacts of extreme climate events on food availability and childhood nutrition in Africa. Specifically, they are examining the impacts of climate induced food shocks on child health measures including child mortality rates. Sam’s previous work examined the non-linear relationship between agricultural productivity and the environment and its effects on human health and the economy. Sam holds a Ph.D. in Agricultural and Resource Economics from the University of California, Berkeley and a B.A. in Statistics and Economics from the same institution.
