An interview with authors of the “The Tropical Oil Crop Revolution” predicts the future of soy and palm oil booms by examining the past and present.

Used in everything from food to fuel, soybean and palm oil have seen production rates skyrocket in the past 20 years. Controversy surrounds the planting of oil crops – cultivated primarily in Southeast Asia and South America – as they are often grown on deforested lands and rely on large farmers and agribusiness rather than smallholders. “The Tropical Oil Crop Revolution: Food, Feed, Fuel, and Forests,” a new book co-authored by Stanford University researchers, examines the economic, social and environmental impacts of the oil crop revolution, and explores how to develop a more sustainable future.

Derek Byerlee, visiting fellow at Stanford’s Center on Food Security and the Environment (FSE), FSE Fellow Walter P. Falcon, and FSE Director Rosamond L. Naylor recently discussed some of their book’s key ideas.

Q: What are the key similarities and differences between the rise of oil crops and the 1965-85 green revolution?

A: From 1990 to 2010, world production of soybean grew by 220 percent and production of palm oil by 300 percent. Like the green revolution for cereal crops, this recent revolution involves two crops – oil palm and soybeans – that dramatically expanded shares in their respective crop subsector – oil crops.

The oil crop revolution differs from its predecessor, the green revolution of rice and wheat, in its mode of expansion. The green revolution embraced tens of millions of producers across many countries, especially where irrigation was available. The oil crop revolution was highly concentrated in a few countries and almost entirely in rainfed areas. Unlike the green revolution, which was spurred on by rapid yield gains, the force behind the oil crop revolution was expansion of crop area. 

Q: What are some ways to improve oil palm sustainability?

A: A lot of faith has been put on certification and private standards and commitments. However, without effective land and forest governance, it will be very difficult for the private sector to operate. The state at both national and local levels will need greatly improved and more transparent systems starting from land and forest tenure laws, information systems, civil service capacity and judicial and redress systems. 

Q: How will the future of oil crops differ from the past?

A: By 2050, we predict demand for oil crops to drop by as much as two-thirds. Demand for biofuel feedstocks cannot maintain the rapid pace of the past decade. Vegetable oils used for food will also grow more slowly. In Asia, population growth will slow and the effects of rising incomes will diminish as consumers in middle-income countries reach high levels of vegetable oil consumption.

The biggest wild card in terms of supply is land availability. Africa has the most land available, however access to clear property rights are often difficult due to “customary rights” to the land. Soybean, a new crop in much of Africa, will increase along with oil palm. We believe the area covered by oil crops does not have to expand greatly; rather, intensification of existing crop land and a modest expansion in area can meet demand. Steady progress is possible through genetic gains in yield. Sufficient degraded land is available for area expansion, provided land governance and incentive systems are developed to steer the expansion onto degraded lands.

Q: How has development of the biodiesel industry affected tropical vegetable oils in the past 25 years, and how will it shape the sector going forward?

A: Before the turn of the 21^st century, few analysts predicted that biodiesel would play a major role in boosting global vegetable oil demand and prices. As it turns out, the expansion of biodiesel markets has been responsible for roughly half of the increase in vegetable oil consumption since 2013. Global biodiesel production more than doubled between 2007 and 2013. By some estimates, it could grow another 50 percent by 2025.

National energy policies continue to play a dominant role in the profitability of the biodiesel industry. The growing response of biofuel policies to low agricultural commodity prices is an important factor that is bound to keep biodiesel in the transportation fuel mix. This is true at least in countries that have strong interests oil crops, such as Indonesia, Malaysia, and Colombia in the case of oil palm, and the U.S., Brazil, and Argentina in the case of soybeans. Without policies mandating the use of biodiesel in fuel mixes, or incentivizing its use, the industry might fade away.

Q: What do you believe is the biggest takeaway from your research?

A: We are cautiously optimistic that the future expansion of the oil crop sector can be managed more sustainably. The predicted slowing of demand and land requirements will reduce pressure on native ecosystems. Several signs point to convergence among global consumers, private business, civil society, and local governments in finding ways to minimize the trade-offs between economic benefits and social and environmental costs.

Derek Byerlee, is an Adjunct Professor in the Global Human Development Program at Georgetown University and Editor-in-Chief of the Global Food Security journal. Walter P. Falcon is the Farnsworth Professor of International Agricultural Policy (Emeritus) at Stanford, senior fellow with the Freeman Spogli Institute for International Studies and the Stanford Woods Institute for the Environment. Rosamond L. Naylor is the William Wrigley Professor in Earth Science and Professor of Economics (by courtesy) and Gloria and Richard Kushel Director, at the Center on Food Security and the Environment Stanford.

By using high-res images taken by the latest generation of compact satellites, Stanford scientists have developed a new capability for estimating crop yields from space. Measuring yields could improve productivity and eventually reduce hunger.

Stanford researchers have developed a new way to estimate crop yields from space, using high-resolution photos snapped by a new wave of compact satellites.

The approach, detailed in the Feb. 13 issue of Proceedings of the National Academy of Sciences, could help estimate agricultural productivity and test intervention strategies in poor regions of the world where data are currently extremely scarce.

“Improving agricultural productivity is going to be one of the main ways to reduce hunger and improve livelihoods in poor parts of the world,” said study-coauthor Marshall Burke, an assistant professor of Earth system science at Stanford’s School of Earth, Energy & Environmental Sciences. “But to improve agricultural productivity, we first have to measure it, and unfortunately this isn’t done on most farms around the world.”

Improved satellites

Earth-observing satellites have been around for over three decades, but most of the imagery they capture has not been of high enough resolution to visualize the very small agricultural fields typical in developing countries. Recently, however, satellites have shrunk in both size and cost while simultaneously improving in resolution, and today there are several companies competing to launch into space refrigerator- and shoebox-sized satellites that take high-resolution images of Earth.

“You can get lots of them up there, all capturing very small parts of the land surface at very high resolution,” said study-coauthor David Lobell, an associate professor of Earth system science. “Any one satellite doesn’t give you very much information, but the constellation of them actually means that you’re covering most of the world at very high resolution and at very low cost. That’s something we never really had even a few years ago.”

Accurate predictions

In the new study, Burke and Lobell set out to test whether the images from this new wave of satellites are good enough to reliably estimate crop yields. The pair focused on an area in western Kenya where there are a lot of smallholder farmers that grow maize, or corn, on small, half-acre or one-acre lots. “This was an area where there was already a lot of existing field work,” Lobell said. “It was an ideal site to test our approach.”

The scientists compared two different methods for estimating agricultural productivity yields using satellite imagery. The first approach involved “ground truthing,” or conducting ground surveys to check the accuracy of yield estimates calculated using the satellite data, which was donated by the company Terra Bella. For this part of the study, Burke and his field team spent weeks conducting house-to-house surveys with his staff, talking to farmers and gathering information about individual farms.

“We get a lot of great data, but it’s incredibly time consuming and fairly expensive, meaning we can only survey at most a thousand or so farmers during one campaign,” said Burke, who is also a Center Fellow at the Stanford Woods Institute for the Environment. “If you want to scale up our operation, you don’t want to have to recollect ground survey data everywhere in the world.”

For this reason, the team also tested an alternative “uncalibrated” approach that did not depend on ground survey data to make predictions. Instead, it uses a computer model of how crops grow, along with information on local weather conditions, to help interpret the satellite imagery and predict yields.

“Just combining the imagery with computer-based crop models allows us to make surprisingly accurate predictions, based on the imagery alone, of actual productivity on the field,” Burke said.

The researchers have plans to scale up their project and test their approach across more of Africa. “Our aspiration is to make accurate seasonal predictions of agricultural productivity for every corner of sub-Saharan Africa,” Burke said. “Our hope is that this approach we’ve developed using satellites could allow a huge leap in in our ability to understand and improve agricultural productivity in poor parts of the world.”

Lobell is also the deputy director of Stanford’s Center on Food Security and the Environment and a senior fellow at the Stanford Woods Institute for the Environment.

Funding for the study, titled “Satellite-based assessment of yield variation and its determinants in smallholder African systems,” was provided by AidData at the College of William and Mary, the USAID Global Development Lab and the Center for Effective Global Action.

Stanford researchers have determined that more than 15 million children are living in high-mortality hotspots across 28 Sub-Saharan African countries, where death rates remain stubbornly high despite progress elsewhere within those countries.

The study, published online Oct. 25 in The Lancet Global Health, is the first to record and analyze local-level mortality variations across a large swath of Sub-Saharan Africa.

These hotspots may remain hidden even as many countries are on track to achieve one of the U.N. Sustainable Development Goals: reducing the mortality rate of children under 5 to 25 per 1,000 by 2030. National averages are typically used for tracking child mortality trends, allowing left-behind regions within countries to remain out of sight — until now.

The senior author of the study is Eran Bendavid, MD, MS, an assistant professor of medicine and core faculty member at Stanford Health Policy. The lead author is Marshall Burke, PhD, an assistant professor of Earth System Science and a fellow at the Freeman Spogli Institute’s Center on Food Security and the Environment.

Decline in under-5 mortality rate

The authors note that the ongoing decline in under-5 mortality worldwide ranks among the most significant public and population health successes of the past 30 years. Deaths of children under the age of 5 years have fallen from nearly 13 million a year in 1990 to fewer than 6 million a year in 2015, even as the world’s under-5 population grew by nearly 100 million children, according to the Institute for Health Metrics and Evaluation.

“However, the amount of variability underlying this broad global progress is substantial,” the authors wrote.

“Mortality numbers are typically tracked at the national level, with the assumption that national differences between countries, such as government spending on health, are what determine progress against mortality,” Bendavid said. “The goal of our work was to understand whether national-level mortality statistics were hiding important variation at the more local level — and then to use this information to shed light on broader mortality trends.”

The authors used data from 82 U.S. Agency for International Development surveys in 28 Sub-Saharan African countries, including information on the location and timing of 3.24 million births and 393,685 deaths of children under 5, to develop high-resolution spatial maps of under-5 mortality from the 1980s through the 2000s.

Using this database, the authors found that local-level factors, such as climate and malaria exposure, were predictive of overall patterns, while national-level factors were relatively poor predictors of child mortality.

Image

Temperature, malaria exposure, civil conflict

“We didn’t see jumps in mortality at country borders, which is what you’d expect if national differences really determined mortality,” said co-author Sam Heft-Neal, PhD, a postdoctoral scholar in Earth System Science. “But we saw a strong relationship between local-level factors and mortality.”

For example, he said, one standard deviation increase in temperature above the local average was related to a 16-percent higher child mortality rate. Local malaria exposure and recent civil conflict were also predictive of mortality.

The authors found that 23 percent of the children in their study countries live in mortality hotspots — places where mortality rates are not declining fast enough to meet the targets of the U.N. Sustainable Development Goals. The majority of these live in just two countries: Nigeria and the Democratic Republic of Congo. In only three countries do fewer than 5 percent of children live in hotspots: Benin, Namibia and Tanzania.

As part of the research, the authors have established a high-resolution mortality database with local-level mortality data spanning the last three decades to provide “new opportunities for a deeper understanding of the role that environmental, economic, or political conditions play in shaping mortality outcomes.”  The database, available at http://fsedata.stanford.edu, is an open-source tool for health and environmental researchers, child-health experts and policymakers.

“Our hope is that the creation of a high-resolution mortality database will provide other researchers new opportunities for deeper understanding of the role that environmental, economic or political conditions play in shaping mortality outcomes,” said Bendavid.  “These data could also improve the targeting of aid to areas where it is most needed.”

The research was supported by a grant from the Stanford Woods Institute for the Environment. 

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

“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/

CONTACTS: 

Neal Jean, School of Engineering: nealjean@stanford.edu, (937) 286-6857

Marshall Burke, School of Earth, Energy and Environmental Sciences: mburke@stanford.edu, (650) 721-2203

Michelle Horton, Center on Food Security and the Environment: mjhorton@stanford.edu, (650) 498-4129