Researchers from the International Center for Tropical Agriculture, working with Colombian Rice Growers Federation, had developed a computer model that weaves together ten years’ worth of agricultural data from specific farms across Colombia. It incorporates information on how individual farmers manage their land — what they planted and how they tended it — what the weather was like during the growing period and the yields each farmer achieved. The idea is for researchers to use the massive data set to identify what kind of agricultural practices have historically worked well in specific locations during particular spells of weather.
When the scientists first trialled the model, the best advice for one group of rice farmers was simply: the climate risks, including drought risk, are too high, so don’t plant.
Several months later, it proved sound advice. Those farmers who missed or ignored the workshops where the advice was imparted lost most of the crops they planted, as drought did indeed hit. But the 170 farmers who heeded the warning saved a collective US$3.8 million worth of seeds and other agricultural inputs.
Last month the project won the Big Data Climate Challenge run by the UN’s Global Pulse initiative, as The Guardian reported. 
I asked Andy Jarvis, one of the project’s lead researchers, what the prize will mean for the future of the model.
Jarvis explains that prizes like this are not necessarily about prestige — “We didn’t even get a certificate” — which usually comes from publishing in top journals. But this kind of prize can open up opportunities for collaborations and funding.
For example, he tells me that part of the prize saw two of the project’s lead scientists, Daniel Jiménez and Sylvain Delerce, meet Rajendra Pachauri, the chair of the Intergovernmental Panel on Climate Change, and Robert Orr, a UN assistant secretary-general, during the UN’s climate summit last month. “They sat with Orr for literally half an hour to go through what they’d done and why this was useful,” says Jarvis.
Although the impacts of this meeting are “probably quite intangible”, he says the visit and the prize more generally have “planted a little seed in a lot of high-level people’s brains” about opportunities for using the emerging field of big data to help advise on good agricultural practices.
Jarvis says the prize has also prompted interest in the project from countries far beyond Latin America. For example, Nigeria’s ministry of agriculture has emailed to congratulate him on the prize, and ask how such data science concepts could help their own farming.
It’s also garnered more interest from the Colombian government. So as well as applying the project in other countries, Jarvis says he hopes to expand it to crops such as maize and beans — and even livestock farming — in the coming years.
Joshua Howgego is SciDev.Net’s deputy news and opinions editor. @jdhowgego