Big Data: Farmers’ New Ally in Fighting Climate Change


Subtle shifts in rainfall plus more extreme climate events force Colombian rice farmers to toss aside familiar assumptions about what varieties to plant and when. Photo: Neil Palmer / CIAT

In the run-up to the United Nations Climate Summit held last September in New York City, CIAT scientists figured among the two overall winners of the Big Data Climate Challenge award. It recognized their novel use of big data tools in collaboration with Colombian partners to help blunt the impacts of climate change on the country’s rice production. Attracting submissions from 40 countries, the competition was hosted by the United Nations Global Pulse, an initiative of the UN Secretary General aimed at harnessing big data, as a public good, for sustainable development.

Reams of rice and weather data

Novel solutions are exactly what Colombian rice farmers urgently need, as subtle shifts in rainfall plus more extreme climate events force them to toss aside familiar assumptions about what varieties to plant and when. In the last 5 years, yields of irrigated rice have declined from an average of 6 tons per hectare to 5 tons, according to Fedearroz, the national rice growers association, and scientists strongly suspect that climate change is the chief culprit. At stake is the ability of Colombia’s rice sector to remain competitive – catering to its own consumers while also trying to generate export earnings – under the country’s trade liberalization policies. Climate change also poses a broader threat to Latin America’s ability to reap its enormous potential as an export-centered granary for the rapidly growing global population. To attack the immediate problem faced by Colombian rice growers, scientists at CIAT and Fedearroz analyzed mounds of data from the latter’s annual rice survey, harvest monitoring dataset, and treasure trove of experimental results on crop management. Researchers also tapped into weather data collected by Fedearroz and the Colombian Institute of Hydrology, Meteorology, and Environmental Studies (IDEAM). Using various data-mining techniques (with names like “artificial neural network” and “dynamic time warp”), they came up with some pretty straightforward conclusions.

From analysis to action

“In a case study carried out in Colombia’s Tolima Department, we observed that a big climate factor limiting yields in some areas is accumulated solar energy during the grain ripening phase,” said CIAT researcher Daniel Jiménez. “To ensure that crops get optimum radiation, farmers can shift the sowing date, and to further reduce yield losses, they can adopt rice varieties that are less sensitive to the amount of radiation received.”

This finding coincides with the results of many years of field research. But the difference is that the big data approach reached this conclusion in just 6 months. It also creates the possibility of linking research with climate data analysis to provide farmers with timely and site-specific recommendations.

Jimenez is part of the crop and climate modeling team in CIAT’s Decision and Policy Analysis (DAPA) Research Area. Their work on rice forms part of a major initiative on climate change, carried out by CIAT in partnership with Colombia’s Ministry of Agriculture and Rural Development (MADR).

The big data approach appears to be working. In Córdoba Department, Fedearroz presented climate simulations to rice growers, which projected low yields under expected weather conditions, including lower rainfall and reduced solar radiation. According to Patricia Guzmán, who manages Fedearroz’s technical department, 170 growers with 1,800 hectares in the Mocarí and La Doctrina irrigation districts followed the recommendation not to plant and thus avoided losing US$3,000, which is what each farmer would have paid to cover production costs.

The sky’s the limit

The scope of the big data approach seems limitless: “As we get more and more data, we’ll soon be able to develop site-specific recommendations for every rice-producing area in Colombia,” said Sylvain Delerce, another member of DAPA’s modeling team and an award co-winner.

Further research will also incorporate data on soils and other factors into the new tools to increase their predictive power. CIAT researchers will also work with the Latin American Fund for Irrigated Rice (FLAR) to scale up the approach with rice growers associations in other countries. DAPA have even gotten a request from Nigeria’s Ministry of Agriculture for assistance in using big data tools to address climate change impacts in the country’s rice sector.

“Climate change obligates us to manage our food systems in a more dynamic way, and big data offers the most effective way to achieve this,” said award co-winner Andy Jarvis, who is DAPA’s director. “Like the hoe and spade, these new tools are becoming crucial implements for global food production.”