New app diagnoses crop diseases

A cassava farmer checks one of her crops infested with the mosaic disease. PHOTO by Lominda Afedraru.

What you need to know:

According to 2016 research published in the Journal of Mobile Computing and Application, mobile agricultural apps show significant potential in the modernisation of the agriculture sector both in developed and developing countries, writes Lominda Afedraru.

A team of scientists in conjunction with the National Crops Resources Research Institute (NaCRRI) Namulonge has developed a mobile phone application which uses artificial intelligence to accurately identify crop pests and diseases in the field.
The app also delivers the latest advice to manage all major diseases and pests that affect root, tuber and banana crops, and helps farmers identify the nearest agricultural extension support for the farmers.

Why the app
The head of Artificial Intelligence and Services Research, Dr Joyce Nakatumba Nabende, explaining modalities of the application of the app notes that the focus of the development of the app was based on farmers helping NaCRRI scientists in identifying the pests and diseases in cassava from the farms in various location of the country.
This, therefore, does not require the scientists to go physically to establish a specific cassava farm, say in Soroti, which is time consuming.
“As smartphones become more common in rural Africa, they also become handy in agricultural productivity. Smallholder farmers or extension officials having basic smartphones with a camera can download the application free of charge, run it up and point the camera at a leaf that has disease indications. They will then get an immediate diagnosis of the disease affecting the plant,” says Dr Nakatumba.

How the app works
She explained that the app works with the provision of central server called add server. The app is downloaded on a smart mobile phone which has been distributed to more than 200 farmers across the country.
It is used for disease surveillance in this case Cassava Brown Streak Virus (CBSV) and Cassava Mosaic Virus (CMV).
A farmer is expected to power the phone and use it for taking pictures of cassava leaf and the tubers which they suspect is not healthy.
The app will be in position to identify if the cassava plant is infected with CBSV or CMV and send the results to the server for the scientist to analyse and advice accordingly.
Once the picture is taken the server will be in position to identify the exact area where it was taken, be it West Nile, Soroti or Lira. It will be able to read the location of the farm and in which village.
Dr Nakatumba and team are now working on apps that will work in pest and disease surveillance in other crops such as maize which will help farmers identify fall army worm infection in their farms.
Other crops in the pipeline are beans, sweet potatoes and rice among others.

Dr Chris Omong the principal investigator of the initiative at NaCRRI notes that the app has helped his team of breeders a great deal.
“Initially we would use naked eyes to observe pest and disease infection of a plant but this app has made our work easy. It allows a scientist to automatically detect how many white flies are on a single leaf. The flies responsible in spreading CBSV. Previously scientists would take the initiative to count the insects on a leaf during research process but this is no more,” he noted.
This app he says will help notice an outbreak of a disease within an identified place in any part of the country through the images sent by the farmers.
This way a team of scientists can be dispatched to carry out analysis and the problem will be solved within the shortest period of time through advising farmers on what to do.
By farmers sending images, scientists have already identified the hot spots of CBSV and that is central region around the Lake Victoria crescent, in Koboko in West Nile and area in Soroti.
At the moment the server is at Makerere Artificial Intelligence Lab but it will be transferred to NaCRRI to be fully managed by the scientists.

Farmers’ knowledge
Joyce Norah Aarakit is a farmer growing cassava on seven acres of land in Ngweri village in Soroti District. She narrates that previously she did not know that some of her plants have been infested with CMV and CBSV until the scientists from Makerere and Naro sensitised them to use the app for disease surveillance.
“We were given smart phones and a provision of data to enable us be online. Right now we are taking photos of cassava leaves and the tubers in our personal farms and for our colleagues as well. We have sensitised farmers in our surrounding communities on how to use the app and they are actively engaged in the initiative,” she explained.
According to Aarakit once you log in and take photos, the app will show you a provision of disease diagnosis. Once you click on it, it will show you the leave is infested with CMV or CBSV.