Contact Us Jobs CIATnet
Select Page

The Challenge

Climate change threatens farmers across the globe by reducing their annual crop yields. We are constantly searching for ways to reduce crop losses caused by climate variability. Farmers in Colombia have been particularly affected as rice production has decreased each year since 2007. These farmers face a particular challenge to understand why their rice yields have dropped by more than one ton over the last five years and are studying ways to reverse this decline.

CIAT’s Role

At CIAT headquarters in Cali, Colombia, scientists are tackling the problem of dwindling rice crop production head-on. They have been reviewing and analyzing mountains of data relating to various aspects of rice crop production. Scientists at CIAT examined harvest monitoring data, climate data and seasonal forecasts, and farming recommendations to develop a series of best agricultural practices. These climate-conscious agricultural practices are a crucial first step toward a decision-making support system for farmers and have made the difference between bankruptcy and viable commercial production for many of them.

Scientists are working in close collaboration with FEDEARROZ, the national rice producers’ federation, which represents more than 50,000 farmers and covers more than 500,000 hectares in Colombia, to share the results and recommendations of this research. They have disseminated their findings through workshops, trainings and ICT applications to extension workers and farming groups across the country.

What has changed?

These research findings have helped CIAT and FEDEARROZ include climate information and recommendations for each of the existing extension sites. These recommendations provide Colombian farmers with planting times that result in the greatest reduction of crop loss, improve total yields and incomes, and increased efficient use of resources.

In Cordoba alone, 170 farmers avoided crop loss in 1800 hectares of irrigated rice, when planting changes were made based on seasonal forecasts from the big data analysis results. This decision alone saved US$3.5 million in input costs.