- Share this article
- Subscribe to our newsletter
New app supports banana farmers
The new app named Tumaini - which means “hope” in Swahili - developed by researchers from the International Center for Tropical Agriculture (CIAT) and Bioversity International aims to help smallholder banana growers quickly detect a disease or pest and prevent a wide outbreak from happening. Tumaini has been freely available since late August 2019. Using artificial intelligence, with an average 90 per cent success rate, the tool can help farmers avoid millions of dollars in losses.
Five major diseases and one common pest can be detected by Tumaini: Xanthomonas wilt of banana (BXW), Fusarium wilt of banana (FWB), black sigatoka (BS), yellow sigatoka (YS) and banana bunchy top disease (BBTV) along with the banana corm weevil (BCW) pest class.
The app could be helpful in the current TR4 outbreak in Latin America since it is trained for fusarium wilt classes. So far, it has been tested in Colombia, the Democratic Republic of the Congo, India, Benin, China and Uganda.
Easy to use for farmers
If farmers see some symptoms on the banana plants, they take a photograph and click the scan button on the app. Then, the probability of disease will be shown in real time. If probability is very high, they click a recommendations button to see the control measures for the particular pest and diseases.
Farmers can also select the plant part where they see the symptoms. Since these major diseases and pest can affect different parts of the banana plant, there are six options, including whole plant, cut fruits, fruit bunches, leaf, and corm roots.
Symptoms can be detected on any part of the crop
Rapid improvements in image-recognition technology made the Tumaini app possible, the researchers say. To build it, they uploaded 20,000 images that depicted various visible banana disease and pest symptoms. With this information, the app scans photos of parts of the fruit, bunch, or plant to determine the nature of the disease or pest. It then provides the steps necessary to address the specific disease. In addition, the app also records the data, including geographic location, and feeds it into a larger database.
Existing crop disease detection models focus primarily on leaf symptoms and can only accurately function when pictures contain detached leaves on a plain background. The novelty of this app is that it can detect symptoms on any part of the crop, explain the researchers, and is trained to be capable of reading images of lower quality, inclusive of background noise, like other plants or leaves, to maximise accuracy.
The app is freely available at the Google Playstore: https://play.google.com/store/apps/details?id=ciat.cgiar.org.tumaini&hl=en
AI-powered banana diseases and pest detection. Plant Methods volume 15, Article number: 92 (2019): https://plantmethods.biomedcentral.com/articles/10.1186/s13007-019-0475-z