A research project has brought together artificial intelligence (AI), satellites, cloud computing and the internet of things (IoT) to help farmers detect diseased bananas using a smartphone app.
The AI tool is built into an app called Tumaini, which means ‘hope’ in Swahili. It uses image recognition technology to scan one of the world’s most popular fruits and detect signs of one of five major diseases and one common pest.
Researchers developed the AI banana app to act as a first line of defence against crop disease at a time when food security faces pressure from an ever-growing world population.
Following tests in Colombia, Democratic Republic of the Congo, India, Benin, China and Uganda, the banana AI tool had a 90% successful detection rate, according to the researchers.
“Farmers around the world struggle to defend their crops from pests and diseases,” said Michael Selvaraj, the lead author of the research, who developed the tool with colleagues from Bioversity International in Africa.
“There is very little data on banana pests and diseases for low-income countries, but an AI tool such as this one offers an opportunity to improve crop surveillance, fast-track control and mitigation efforts, and help farmers to prevent production losses.”
The researchers at Bioversity International were joined by the Imayam Institute of Agriculture and Technology (IIAT), India, and Texas A&M University, US. The findings were published in the journal Plant Methods.
How the banana AI app works
The banana AI app uses deep learning, a subset of artificial intelligence, to detect diseased bananas. The algorithms were initially programmed to look for specific characteristics that indicate a diseased banana. With these parameters, the algorithm was fed 20,000 images of various visible banana disease and pest symptoms, improving its accuracy with each scanned image.
“The overall high accuracy rates obtained while testing the beta version of the app show that Tumaini has what it takes to become a very useful early disease and pest detection tool,” said Guy Blomme, from Bioversity International.
“It has great potential for eventual integration into a fully automated mobile app that integrates drone and satellite imagery to help millions of banana farmers in low-income countries have just-in-time access to information on crop diseases.”
After diagnosing the banana, the app provides the farmer with the next steps to take to treat the disease.
Where other crop disease detection models focus on the leaves, the AI banana app can detect symptoms anywhere on the crop. It can also work even when image quality is low.
The app also feeds the data, including geographic location, into a larger database that will eventually combine with satellite imagery and climate information. This will give farmers a holistic view of disease outbreaks, allowing them to take better preventative measures.
“This is not just an app,” said Selvaraj. “But a tool that contributes to an early warning system that supports farmers directly, enabling better crop protection and development and decision making to address food security.”
Verdict deals analysis methodology
This analysis considers only announced and completed deals from the GlobalData financial deals database and excludes all terminated and rumoured deals. Country and industry are defined according to the headquarters and dominant industry of the target firm. The term ‘acquisition’ refers to both completed deals and those in the bidding stage.
GlobalData tracks real-time data concerning all merger and acquisition, private equity/venture capital and asset transaction activity around the world from thousands of company websites and other reliable sources.
More in-depth reports and analysis on all reported deals are available for subscribers to GlobalData’s deals database.