Innovations in Global Health: CIAT Using Big Data and Machine Learning to Predict Food Shortages in Africa

Ian MatthewsBlog

A new series featuring promising product or service innovations in global health

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.

The organization is developing a Nutrition Early Warning System (NEWS) – a tool using advances in machine learning and artificial intelligence to process a wide assortment of data to better anticipate and avoid food crises. The service is intended to help decision makers take early action to resolve problems that have historically produced high levels of malnutrition in poor countries in the past. It will initially focus on boosting nutrition in sub-Saharan Africa, but eventually will target vulnerable populations globally.

 

 

Using machine learning, by which computers track complex and constantly changing data in order to “learn” and make predictions, NEWS will search for food shortage triggers – signs of potential crop failures, drought, rising food prices. Over time, the system becomes “smarter” and more accurate. Current efforts to address food crises are often hampered by four key shortcomings, which NEWS seeks to address:

  • Responses are reactive, not proactive. Most resources and interventions are reactive; they focus on crisis response rather than preventing problems from progressing that far.
  • Interventions are limited to the household and community level. Nutrition interventions typically focus on building household resilience within communities. There is less emphasis on building resilience within national and regional food systems.
  • Decision-makers lack the data to combat malnutrition. There is no single, global system collecting, tracking and processing the many different indicators of malnutrition, which deprives decision-makers of critical insights that could drive more effective solutions.
  • Signs of malnutrition may not become apparent until a food crisis erupts. It can be difficult to detect the subtle factors that inevitably produce food shortages and chronic malnutrition before conditions degrade and hunger sets in.

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.

The NEWS system would enable governments, donors, farmers, relief agencies, NGOs and others to implement more rapid, tailored interventions to prevent food crises. This white paper calls for collaboration to find robust methods to track indicators of malnutrition in West, East and Central, and Southern Africa. CIAT urges potential partners who want to use big data approaches to address fundamental challenges linked to agriculture to join CIAT’s effort to develop the potential of NEWS.

To learn more about NEWS and CIAT click the link or email Debisi Araba, CGIAR’s Regional Director for Africa.

Media courtesy of CIAT

Ian MatthewsInnovations in Global Health: CIAT Using Big Data and Machine Learning to Predict Food Shortages in Africa