Bananas are one of the most widely consumed fruits and are marketable fruit crops grown all over the world. It helps lower high blood pressure and reduces the risks of cancer.
However, numerous diseases and pests affect the production of bananas worldwide. Smallholder farmers, representing 85% of the world’s farms, face many toxic and biotic problems. Many banana pests and diseases have caused significant yield losses across the production landscape and are a significant threat to global food security. Therefore, early diagnosis of pest and field diseases is the first crucial step.
Early detection of crop diseases or pests can lead to rapid intervention, reducing the impact on food supply chains.
Therefore, an international team of researchers has developed a new artificial intelligence (AI) tool, which allows banana formers to identify diseases and pests in the early stages. An easy-to-use smartphone tool designed for farmers scans plants for signs of five major diseases and one common pest and help farmers avoid millions of dollars in losses.
The tool is now an app called Tumaini – which means “Hope” in Swahili – that can be used both on and offline and is claimed to operate with an accuracy of more than 90% in most of the models tested.
The new smartphone-assisted disease diagnosis method could pave the way towards creating a satellite-powered, globally connected network to control disease and pest outbreaks.
“Farmers around the world struggle to defend their crops from pests and diseases,” said Michael Selvaraj, the lead author, 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 Tumaini app is based on improved image recognition technology and deep learning. Researchers uploaded 20,000 images describing various banana diseases and pest symptoms, which helps the tool to learn how to identify specific signs of infection or infestation, as well as which steps to take to counter the problem. In addition, the app also records the data, including geographic location, and feeds it into a larger database.
The smartphone-based disease detection tool is tested in Colombia, the Democratic Republic of the Congo, India, Benin, China, and Uganda, where the app had a detection accuracy of more than 90%.
“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.”
The findings are published in the journal Plant Methods.
