YesAmy Selim walked among the dense, bright green bushes on the slopes of her coffee farm in the village of Sorwot in Kericho, Kenya, accompanied by a young farmer named Kennedy Kirui. They stopped at every corner to enter the farm’s coordinates into a WhatsApp conversation.
The conversation was with Virtual Agronomist, a tool that uses artificial intelligence to provide fertilizer application advice through chat messages. The chatbot asked a few more questions before producing a report that said Selim should aim for a yield of 7.9 tonnes and use three types of fertilizers in specific quantities to achieve that goal.
“My God!” Selim said upon receiving the report. I had planned to use much more fertilizer than Virtual Agronomist recommended. “I could have wasted the money.”
In Kericho and other parts of Kenya, AI-based tools have become increasingly popular among smallholder farmers seeking to improve the quality and quantity of their produce.
Pests, diseases and lack of technical knowledge mean that farmers have become accustomed to suffering large-scale crop losses. They used to rely on the advice of agricultural extension officers (professionals deployed by local governments to provide educational services to farmers), but their numbers have declined in recent years due to inadequate funding.
Selim started using Virtual Agronomist on his 0.4 hectare (1 acre) farm in 2022, with the help of another farmer who had a smartphone at the time. Following his recommendations, his farm produced 7.3 tons of coffee, the highest yield in its history. He is optimistic that the new set of recommendations will work this time as well. “Technology helps,” he said.
Before adopting Virtual Agronomist, Selim simply applied fertilizers using what he described as “general farmer knowledge,” applying different types at different times of the year without knowing the health of the soil. The productivity of the farm was low. In one season he managed to produce only 2.3 tons of coffee.
At other times, he would take samples of his soil for analysis in laboratories far from Sorwot, but the results would take months to arrive, and sometimes not at all.
“A big challenge for farmers is not knowing exactly what their soil needs,” said Florah Maritim, factory manager of the Sorwot Coffee Growers Cooperative Society, which pulps and dries coffee from local farmers.
The story is similar for farmers trying to determine what pests and diseases have affected their crops.
Musau Mutisya, from Kwa Mwaura village in Machakos County, said he used to rely on his own knowledge to identify pests and diseases, but it was not always accurate.
On a recent sunny morning on his 1.5-acre (0.6 hectare) farm, he stood next to a corn plant, pointing his phone’s camera at a torn and torn leaf using PlantVillage, an intelligence-powered app artificial to diagnose pests and diseases.
A voice assistant told him where to hold the phone, identified the pest as the fall armyworm, and then gave him advice on how to control it. “In the past we were guessing,” he said. “You’ll end up using more money trying what you don’t know.”
Both tools work by training AI models with images and data. PlantVillage researchers fed their model thousands of images of healthy and diseased crops to help it learn to identify pests, while Virtual Agronomist researchers trained a model to predict PH and other soil properties using satellite data from across the continent. .
There is seven and a half million small farmers in Kenya. But the country has a ratio of extension officers to farm households of 1:1093, much higher than the 1:400 ratio recommended by the Food and Agriculture Organization.
Farmers need information to be successful, said Enock Chikava, director of agricultural delivery systems at the Gates Foundation, which supports the nonprofit iSDA that created Virtual Agronomist. Technology can help fill the gap left by the lack of extension agents, he said. “We believe in the power of digital,” Chikava said. “It can really shake things up.”
TO published report In July, the GSM Association found that the majority of AI use cases in Kenya, Nigeria and South Africa were in agriculture and food security.
The report says the potential for technology to support socio-economic growth on the continent is enormous, but achieving this requires efforts to address the digital skills shortage and put more smartphones in people’s hands.
Both PlantVillage and Virtual Agronomist use a “lead farmer” model, whereby farmers with smartphones are trained to use the tools not only on their own farms but also on neighboring plots. PlantVillage is free to use, as is Virtual Agronomist for all crops except coffee, for which it charges KSh300 (around £1.70) for advice.
Despite the promise, some scientists warn about dependence on AI tools for agriculture. Angeline Wairegi, who has investigated on the use of technology in agriculture in East Africa, said that most AI training data sets exclude indigenous knowledge, meaning the information they provide can exclude successful localized practices.
“Heavy reliance on AI tools to establish agricultural practices may result in the erosion of long-established and proven indigenous agricultural practices,” said Wairegi, founder and research director of Athene Research Group.
But for farmers like Boniface Nzivo in Mua village in Machakos County, AI is a game-changer. It uses a system called FarmShield to monitor temperature, humidity and soil moisture and advises you when to water your cucumbers, things you used to have trouble with.
“I don’t waste time trying to figure out how much water to use,” he said while inside a greenhouse to grow the plant, which needs a constant supply of water. “It’s great technology.”