How Colombian Corn Farmers Are Using Tech to Boost Yields

As extreme droughts and floods wreak havoc on farmers’ fields around the world, scientists may have found a solution that allows producers to navigate the effects of climate change.

A partnership between Colombia’s federal government, a national farming organization and scientists at the International Center for Tropical Agriculture (CIAT) created a data-driven study that helped farmers in the country’s Cordoba region grow crop yields from an average of 3.5 tons per hectare to more than 6 tons per hectare.

The initiative used machine learning algorithms to analyze weather data, as well as crop data collected from local farmers. The four-year study, published in the journal Global Food Security, was inspired by a number of small-scale maize farmers in the area who struggled with constant weather-related disasters wiping out their crops.

Researchers collected data from multiple sources, including small-scale farmers. Using artificial intelligence and expert opinion, they were able to determine how the variation of weather, soils and management practices impact maize yields. This information was then used to create guidelines that helped maize farmers to produce high, stable yields.  

“With institutions, experts and farmers working together, we overcame difficulties and reached our goals,” said Daniel Jimenez, lead author of the study and data scientist at CIAT, in a news release.

In addition to helping farmers mitigate the impacts of erratic weather, the program helped reduce farmers’ fertilizer costs.

Scientists are confident that the results provide a foundation for future projects that marry tech and agriculture. But Jimenez said that opportunities will be dependent on whether the private sector becomes involved in developing sustainable systems for capturing, analyzing and distributing information.

“In the future we can envisage every field being carefully characterized and monitored, turning the landscape into a whole series of experiments that provide data which machine learning can interpret to help farmers manage their crops better,” he said.