Mapping Research on Small-Scale Farms

Photo: Georgina Smith / CIAT

Using machine learning to map a million data points from agricultural research from the Global South

The evidence base on agri-food systems is growing exponentially. The CoSAI-commissioned study, Mining the Gaps, applied artificial intelligence to mine more than 1.2 million publications for data, creating a clearer picture of what research has been conducted on small-scale farming and post-production systems from 2000 to the present, and where evidence gaps exist.

The study used Havos AI machine learning models to extract information from each publication based on a series of modular questions. Graphical maps of the data provide policymakers and funders with a more nuanced view of the information available, which can help them to prioritize and coordinate international funding and research efforts.

Find out more in this CoSAI policy brief.

ACTIONS NEEDED

  • Research and innovation for agri-food systems should routinely integrate measurements on social equity and health outcomes. Only a fraction of publications focus on outcomes related to people, such as health and nutrition. The gaps are stark around social equity and inclusion outcomes, such as for women and elderly, indigenous and youth populations.

  • Research and innovation organizations should prioritize programs that go beyond measuring farm and household level outcomes. There has been relatively little attention to landscape or macro level analyses that are especially important for the natural environment.

  • Research organizations should fast-track research on ecosystems, biodiversity and climate change in various climate zones. Research on ecosystem services is limited compared to research on technological and socio-economic innovations.

  • Funders should invest in opportunities to increase global research efficiency through identifying and sharing research. South–South cross-learning increases efficiency and the speed of innovation – and most research on Global South agriculture is being led by researchers in the Global South. Better platforms and toolkits using machine learning will help researchers and decision makers use existing data better.

 

Read our policy brief to learn more.