Chronic malnutrition affects one in four people in sub-Saharan Africa. This increases the region’s vulnerability during food crises and compromises the continent’s overall development. We know we need to improve the way we respond to food crises to protect African food production systems, farmers, and the people who depend on the food they produce.
Food crisis response
Currently responses to food crises are reactive, not proactive. Signs of malnutrition may not be apparent until a food crisis erupts, and decision-makers lack the data to combat crises, making response coordination difficult.
There are various forces that influence nutrition and it can be difficult to identify how they converge to cause widespread problems. In addition, most governments and aid organizations use multiple metrics and separate tracking systems to measure malnutrition. With so much data to absorb, it can be easy to miss early indicators of trouble brewing before a crisis kicks in.
This makes it impossible to form proactive food policies and escape the trap of constantly reacting to disruptions rather than getting ahead of hunger. Interventions are also limited to the household or community level and rarely focus on national and regional systems.
How data will help
An innovative new approach to collating and analysing large sets of data could enable this shift to early action. Through machine learning, computer programs track complex and constantly changing data from multiple sources in order to “learn” from them and make predictions.
The International Center for Tropical Agriculture (CIAT) is applying machine learning technology to search for early signs of potential crop failures, drought, rising food prices, and other factors that can trigger food shortages. Over time, this bespoke system – known as the Nutrition Early Warning System (NEWS) – will become “smarter” and more accurate so that data can be used to predict the likelihood of malnutrition threats before they occur, while also suggesting mitigating measures.
NEWS would enable governments, donors, farmers, health care providers, NGOs and food companies to contribute towards and implement more rapid, tailored interventions.
CIAT will coordinate the development of NEWS, to be deployed in collaboration with partners to alert decision-makers to nutrition threats well ahead of a crisis. Initially, CIAT will use NEWS to focus on boosting nutrition in sub-Saharan Africa. By picking up food shortage triggers, the system will give relief agencies, donors and governments information they need to make informed decisions about agricultural policies and programmes.
Ongoing surveillance is expected to provide multiple recommendations for future nutrition interventions. The recommendations can be tailored to the needs of individual countries through national “nutrition dashboards”. These will further refine insights available through NEWS. The dashboards will be accessible via a secure website that will regularly monitor and post updates on key nutrition and food security indicators.
Refining NEWS for Africa
CIAT, which leads the CGIAR Platform for Big Data in Agriculture, has already seen success 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 analyse 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.
We now need to work with partners to track indicators of malnutrition in West, East and Central, and Southern Africa and to create and fully develop NEWS.
The NEWS white paper calls for collaboration between governments, development and relief agencies to find robust methods to track malnutrition indicators. In particular, it urges potential partners who want to harness big data to address fundamental challenges linked to agriculture and nutrition in the developing world, to join CIAT’s effort to create and fully develop the potential of NEWS across Africa.
The opinions represented in this blog do not necessarily reflect those of individual Malabo Montpellier Panel members and their organisations. Originally published on Farming First.