The project aims to deliver open, accessible, and quality machine learning datasets for crop pests and disease diagnosis based on crop imagery and spectrometry data from Uganda, Tanzania, Namibia, and Ghana. The development of beneficial and effective real-world machine-learning applications require localized and labeled pest and disease datasets. This project will provide these appropriate image datasets for food security crops grown in sub- Saharan Africa: Cassava, Maize, Beans, Bananas, Pearl Millet, and Cocoa. In collaboration with the national agricultural experts, this study will deliver on a two-way data set approach for crop pests and diseases: (a) A field-level Geo-coded and time-stamped dataset of 145,000 images representing diseased and healthy cassava, maize, beans, bananas, pearl millet, and cocoa crops. (b) A dataset of 8160 cassava spectra and 2000 spectra points of maize and pearl millet representing disease manifestations before symptoms are visibly seen by the human eye.

We use artificial intelligence to mine data from local village radio stations to generate timely data on crop pests and disease in sub-Saharan Africa. Crop loss due to pests and disease threatens the economic survival of smallholder farmers, and access to surveillance data is critically important yet often not affordable. Local radio shows are a powerful source of information flow in rural African villages: they cover topics including politics, policy, climate, and social circumstances, in addition to crop concerns. Collectively, this information provides a holistic representation of current events in these communities. They will analyze local broadcasts to generate crop surveillance data that is linked to the local community situation.Radio content will be collected at low cost through a collaboration with Pulse Labs Kampala, and they will build artificial intelligence models based on deep neural networks and keyword identification to mine the data.The results will be combined with photographs of diseased crops provided by local farmers and used to train machine learning models to ultimately extract radio information in multiple languages and with diverse accents. This project will provide near real-time crop surveillance data and allow for timely responses to threats.