Artificial Intelligence offers banana growers the possibility to protect the world’s most popular fruit

Farming and agriculture has increasingly adopted to using Artificial Intelligence powered tools. The advent of AI reaching even in the remotest corners of the globe are bringing smallholder farmers closer to markets, extension workers, in addition to providing information on climate and satellite images.  In addition, it has also helped them fight against a harvest destroying pests and diseases.

In the latest cutting-edge discovery, a team of researchers from India’s Imayam Institute of Agriculture and Technology (IIAT), and Texas A&M University, created a smartphone tool which could help banana farmers to scan plants affected by five major diseases and by a common pest. A 90 percent detection rate was observed through its testing in Colombia, the Democratic Republic of the Congo, India, Benin, China, and Uganda.

“Farmers around the world struggle to defend their crops from pests and diseases,” commented Michael Selvaraj. He is the lead author, who developed the tool along with fellow researchers 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,” he added.

Banana is regarded one of the most essential staple foods around the world, but it is increasingly attacked by Xanthomanas wilt, Fusarium wilt, and black leaf streak (or Black sigatoka).

The smartphone tool has been built in an app called the Tumaini. The word means ‘hope’ in Swahili and is especially designed to help smallholder banana growers to instantly detect a disease or pest and thus prevent a possible outbreak of an epidemic. The app also helps banana farmers to link to extension workers which can instantly stem the outbreak from occurring.

Furthermore, the tool can also upload data to a global system for the purpose of large-scale monitoring and control. Researchers claim the goal of the app is to solely help banana farmers in order to control a disease.

“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,” according to 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,” he concludes.

The research study based on the smartphone tool has been published this week in the journal Plant Methods.

Reports allege frequent improvements in the image-recognition technology which led to the creation of the Tumaini app. For the app, experts uploaded 20,000 images which portrayed banana diseases and its pest symptoms. Based on the information, the app could scan photos of various parts of the fruit, plant or a bunch and hence help in determining the nature of the pest or the disease. The app then addresses the necessary steps which are required to tackle the specific disease. Additionally, the app also stores data, along with the geographical location, and feeds this information into a larger database.

“This is not just an app,” commented 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.”