Nutrition Early Warning System (NEWS) white paper signals unprecedented shift from crisis response to early action, using Big Data and machine learning
29 May 2017, NAIROBI, KENYA — A new approach to predict and track malnutrition in Africa-- driven by the same advanced technology now powering everything from Internet search-engines to consumer fraud protection—could help trigger a shift from crisis response to early action against hunger, according to scientists.
A Nutrition Early Warning System (NEWS), outlined in a white paper published today by the International Center for Tropical Agriculture (CIAT), would use cutting-edge big data approaches to process large volumes of information from multiple sources to detect early signs of food shortages and raise the alarm about impending crises.
With one in four people in sub-Saharan Africa malnourished, and famine and food shortages already affecting South Sudan and looming in northern Nigeria and Somalia, the approach aims to fast-track solutions to meet global commitments to end hunger and malnutrition by 2030.
“Since the 1970s, sub-Saharan Africa has been hit by food crises with depressing frequency,” said Dr. Mercy Lung’aho, a CIAT nutritionist and lead author of the white paper. “This tells us that something is fundamentally wrong with our food system and with the way we’re tracking crisis signals.”
“NEWS would enable us to identify trends and risks way ahead of time, allowing policymakers to take evasive action before disaster strikes.”
Big Data and Machine Learning
Initially, NEWS would focus on boosting nutrition in sub-Saharan Africa by responding to triggers and allowing relief agencies, donors and governments to make more informed decisions. A prototype is currently being developed by CIAT to be deployed in future in alliance with key partners.
NEWS is based on a technique known as machine learning, by which computers track complex and constantly changing data in order to “learn” and make predictions. NEWS would apply this technology to search for early signs of potential crop failures, drought, rising food prices, and other factors that can trigger food shortages. Over time, the system becomes “smarter” and more accurate.
CIAT, which leads the CGIAR Platform for Big Data in Agriculture, has already seen success with using big data approaches to tackle agricultural challenges. In 2014, some 170 farmers in Colombia avoided potentially catastrophic losses after CIAT experts used a machine learning algorithm to analyze weather and crop data. It revealed drought on the horizon, and farmers were advised to skip a planting season, saving them more than US$3 million in input costs.
Cutting Through Complex Food Data
Currently, most governments and aid organizations use multiple metrics and separate tracking systems to measure malnutrition. And with so much data to absorb, it can be easy to miss early indicators of trouble that can be brewing years before a crisis kicks in.
“This makes it hard to formulate a proactive food policy and escape the trap of constantly reacting to disruptions rather than getting out ahead of hunger,” said Dr. Debisi Araba, CIAT’s Regional Director for Africa.
“But the same confusion related to food data can delay interventions: this is exactly the kind of complexity the NEWS system would be designed to handle. It would mean that instead of fighting fires, we can help prevent them from happening.”
More broadly, the NEWS system would enable governments, donors, farmers, health care providers, NGOs and food companies to contribute towards and implement more rapid, tailored interventions.
The white paper calls for collaboration between governments, development and relief agencies to find robust methods to track indicators of malnutrition in West, East and Central, and Southern Africa.
In particular, it urges potential partners who want to use big data approaches to address fundamental challenges linked to agriculture in the developing world to join CIAT’s effort to create and fully develop the potential of NEWS.
The International Center for Tropical Agriculture (CIAT) is a scientific research organization committed to sustainable food production and improving rural livelihoods in Africa, Asia and Latin America. As well as developing new techniques and approaches to make agriculture more profitable, competitive and sustainable, for 50 years CIAT has been a trusted provider of impartial advice on agricultural and environmental issues to governments and policymakers all over the world. www.ciat.cgiar.org. CIAT is a CGIAR Center.
CGIAR is a global research partnership for a food secure future. CGIAR science is dedicated to reducing poverty, enhancing food and nutrition security, and improving natural resources and ecosystem services. Its research is carried out by 15 CGIAR Centers in close collaboration with hundreds of partners, including national and regional research institutes, civil society organizations, academia, development organizations and the private sector. www.cgiar.org