KIGALI, August 5 (IPS) – A group of scientists engaged in finding solutions to mitigate the impact of a banana virus in Burundi has developed an Artificial Intelligence (AI) tool. ) for disease monitoring.
Food and Agriculture Organization of the United Nations (FAO) Research indicates that Banana Leaf Blight Disease (BBTD), caused by Banana Leaf Head Disease Virus (BBTV), is endemic in many banana-producing countries in sub-Saharan Africa.
The virus was first reported in the Democratic Republic of the Congo (DRC) in the 1950s and has entered and spread to 15 countries in sub-Saharan Africa.
The disease has been reported in Angola, Benin, Burundi, Cameroon, Central African Republic, Republic of the Congo, DRC, Equatorial Guinea, Gabon, Malawi, Mozambique, Nigeria, Rwanda, South Africa and Zambia. However, the latest findings show that BBTD is currently a major threat to banana farming and a threat to more than 100 million people for whom bananas are a staple food.
The AI development team, led by Dr Guy Blomme and his colleague Dr Michael Gomez Selvaraj from Alliance of Bioversity and CIAT (ABC), tested the detection of banana plants and their major diseases through aerial photography and machine learning methods.
This project aims to develop an AI-based banana disease and pest detection system using Deep Neural Networks (DCNN) to assist banana farmers.
While farmers struggle to protect their crops from pests and diseases, scientists from ABC have created an easy-to-use tool to detect banana pests.
The tool, which has been shown to have 90% success in detection in a few countries, such as the DRC and Uganda, is an important step towards creating one, the researchers say. A globally connected network powered by satellites to control disease and pest outbreaks.
During the pilot phase, in collaboration with a team from Burundi’s national agricultural research organization – ISABUTwo sites where banana leaf head disease is endemic in Cibitoke province were compared with the disease-free area in Gitega province (Central region).
Cibitoke Province is endemic to the BBTD and lies within the border area with Rwanda and the Democratic Republic of Congo (DRC).
Performance and validation metrics were also calculated to measure the accuracy of different models in automated disease detection methods by applying modern deep learning techniques to detect banana disease and Pest symptoms are visible on different parts of the plant.
Researchers have come up with reasons why it’s so important to detect disease in bananas.
“In East and Central Africa, it is an important component of the diet, accounting for more than 50% of total daily food intake in parts of Uganda and Rwanda.”
Bananas are also a major crop in Burundi. Cultivated land area is estimated at 200,000 to 300,000 ha, accounting for 20 to 30% of agricultural land.
Data from the Burundian Ministry of Agriculture and Livestock shows that food and nutrition security continues to deteriorate, with 21% of the population being food insecure. They say this can be aggravated by various plant diseases such as BBTD.
While bananas are vital to food security and people’s livelihoods, experts also say that BBTD can have devastating social and economic effects on the continent.
Bonaventure Omondi, CGIAR researcher who collaborated on this project, said: “Based on the fact that when BBTD appeared, it was initially a very confusing disease and did not present spectacular symptoms. . IPS in an interview. While it is important to stop the epidemic early, it is also a challenge, which is why AI solutions are important.
Agricultural experts say that the East African Plateau is an area of secondary diversity for a type of banana known as the AAA-EA type. This type of banana is genetically close to dessert bananas but has been selected for use in beer, cooking and dessert bananas.
Banana cultivation in Burundi is divided into three different categories. Bananas for beer/wine production, of which the juice is extracted and fermented, accounts for about 77% of national production by volume. Fourteen percent of bananas are grown for cooking, and in the end, about five percent are dessert bananas that are cooked and eaten directly.
With recent advances in machine learning, researchers believe that new disease diagnosis based on automatic image recognition is technically feasible.
“Minimizing the impact of disease threats and maintaining a mixed landscape matrix of banana and non-banana canopy are important steps in managing a large number of diseases and pests,” said Omondi. ,” Omondi said.
As an example of how this emerging technology works, the researchers focused on data sets described on banana plants with disease symptoms and established algorithms to help identify diseased plantations.
Prosper Ntirampeba, a banana grower from Cibitoke province in northwestern Burundi, told IPS he harvested fewer bunches of bananas in his most recent crop because BBTD spread through his farmland.
“We have been forced to uproot the infected trees since the disease reached our main production area,” he said. This leads to a greater cost burden.
In another case, when BBTD was discovered, agricultural officials under the guidance of the researchers advised farmers to remove all infected ‘carpets’ where several hectares of trees were infected. disease has been eliminated. This is the key to eliminating the epidemic in Busoni, a remote rural village in North Burundi.
Although some farmers are often resistant to uprooting their banana trees, Ntirampeba said it’s important to get rid of the disease.
“This disease can threaten the livelihoods of most farmers who depend on crops,” he told IPS.
Currently, other new disease surveillance methods are also being developed by ABC researchers in Burundi, including drone-based surveillance for local disease risk identification and identification. recovery areas.
Report of the United Nations Office IPS
By @IPSNewsUNBureau
Follow IPS News UN Office on Instagram
© Inter Press Service (2022) – All rights reservedOrigin: Inter Press Service
