A Ghanaian Artificial Intelligence entity, karaAgro AI, and its consortium partners have been awarded a grant by Lacuna Fund towards the creation of a machine learning dataset for crop disease and pest detection.
The consortium partners include the Makarere University (Uganda), the Nelson Mandela African Institution of Science and Technology (Tanzania) and Namibia University of Science and Technology - NUST (Namibia).
Lacuna Fund covers as much as $500,000 budget per project.
Mr Darlington Akogo, Founder and Executive Director of karaAgro AI, and the Lead of the Ghana implementation of the fund and project, who announced this to the Ghana News Agency, said his outfit would be supported by the Department of Crop Science of the University Of Ghana, and the Cocoa Research Institute of Ghana (CRIG) towards the collection, annotation and baseline modelling of crop disease and pests in Ghana.
"With this funding, we can collect largely localised crop disease and pest data, which can be used towards improving African Artificial Intelligence-for-Agriculture solutions like the karaAgro AI Android app.
African farmers, who currently lose up to 40 per cent of crop yield due to diseases and pests, would then be able to affordably detect diseases and pests, and boost their yields, using these AI-powered automated tools on mobile devices," Mr Akogo said.
He said karaAgro AI is well-positioned for the creation of machine learning datasets for crop pest and disease diagnosis based on crop imagery and spectrometry data and hope to lead the charge.
"This project is a unique collaboration across four countries in sub-Saharan Africa with the aim of delivering crop imagery and spectrometry datasets for six important food security crops. The datasets are necessary for building machine learning models for early disease diagnosis and will be relevant for not only the AI and machine learning communities but also for the smallholder farmers and agricultural experts," Joyce Nakatumba-Nabende of Makarere University said.
This project would produce quality, open and accessible image and spectrometry datasets from Ghana, Uganda, Tanzania and Namibia for several crops that contribute to food security in Sub-Saharan Africa, including cassava, maize, beans, bananas, pearl millet, and cocoa.
The team, composed of data scientists and researchers from Makerere University, The Nelson-Mandela African Institution of Science and Technology, Namibia University of Science and Technology, and the karaAgro AI Foundation, expect the image and spectral datasets would be used for early disease identification, disease diagnosis, and modelling disease spread, which will ultimately help in breeding resistant crop varieties.