Cassava is the staple of more than 500m people across Africa. A woody root vegetable, it can be steamed, boiled, baked or mashed and is the major source of calories for nearly two out of five Africans.
But how do you protect a major crop from diseases when it’s predominantly grown by smallholders in rural areas? Simple: there’s an app for that.
Researchers from Penn State University, alongside the Consultative Group for International Agricultural Research (CGIAR), have been developing a smartphone app that uses camera and AI technology to help farmers spot the early signs of these and several other diseases.
“Smallholders or extension officers with a basic smartphone with a camera will be able to download the app for free, fire it up, point it at a leaf with disease symptoms and get an instant diagnosis. That’s truly revolutionary,” said David Hughes, associate professor of entomology and biology at Penn State University.
In 2014 more than 145m tonnes of cassava was harvested across Africa alone. It makes a great staple because it is grows under tough conditions, needs little nutrients and is reasonably resistant to climate change. But two particular strains of disease – cassava brown streak and cassava mosaic disease – are threatening the incomes and food security of an estimated 30m farmers in East and Central Africa.
With the app, farmers can simply take a picture of the plant’s leaves and the phone will instantly can identify the signs of the disease and suggest appropriate action. During trials in Tanzania, the app recognised diseases in the field with 98% accuracy.
But what makes the app novel is that all the processing is done on the phone itself – unlike most other AI processes, including smart assistants, that send data over the internet to more powerful computers for processing. This is important because, while smartphones are now becoming prevalent across Africa, poor infrastructure sometimes means an internet connection is not always available.
The app was also specially designed to work on less expensive phones with lower computing power.
Putting this application on a smartphone can compensate for the lack of access to trained plant disease experts, a particular problem for smallholders and farmers in rural areas with poor access infrastructure.
Late last year Penn State was awarded $100,000 to help develop the app. They started with cassava and plan to develop it to cover other crops, including bananas and roots and tubers such as potatoes. The team is also looking to connect the app to Vodaphone’s DigiFarm platform, which connects African farmers, so text alerts can be sent about disease outbreaks.
☛ Want to stay up to date with the news? Sign up to our daily bulletin.