AI Tool AAgWa to Revolutionize Crop Tracking and Prediction in Africa

• The Africa Agriculture Watch (AAgWa), an innovative AI tool developed by AKADEMIYA2063, aims to revolutionize the agriculture sector in Africa by accurately tracking and predicting crop rotations and yields, thereby assisting in mitigating food crises.
• While AAgWa leverages advanced technologies such as machine learning and remote sensing for accurate crop production data, it faces the challenge of simplifying this complex data into understandable and useful information for the average farmer.

A revolutionary artificial intelligence (AI) tool known as Africa Agriculture Watch (AAgWa), developed by AKADEMIYA2063, is set to transform the agriculture sector in Africa. By accurately tracking and predicting crop rotations and yields, AAgWa promises to be an invaluable tool to help mitigate food crises across the continent.

“Conventional analytic techniques alone are insufficient to meet the challenges we face in agricultural decision-making,” commented Racine Ly, the director of data management for the project, in a recent interview with Science X. “To ensure effective decisions, it is crucial that the data we use is correct and the predictions accurate.”

The AAgWa tool will focus on the production of staple foods such as maize, cassava, and sorghum. According to the AKADEMIYA2063 organization, the platform, launched in late April, allows the public to access and interpret data on crop yields and production by region.

Furthermore, AAgWa is designed to help Africa weather system shocks, including severe weather events, plant diseases, pest outbreaks, and health emergencies such as COVID-19, which have disrupted crop care.

To create its predictions, the program takes into account several factors, including the “Normalized Difference Vegetation Index” (a ratio of different wavelengths of light needed by crops), daytime land surface temperature, rainfall data, and information on underground water supply and routes.

Historical data is also utilized by the program to generate a crop map, which indicates where crops have grown and are likely to grow again, as well as to provide a general crop calendar.

“Recent developments in machine learning and computer modeling allow us to track and predict crop production using remotely sensed data,” the group said in a statement. “These digital technologies offer the ability to overcome the obstacles to data gathering during crises and access to good quality agricultural statistics.”

However, the challenge lies in translating these complex big data tools into information that the average farmer can understand and utilize. “We plan to collaborate with cooperatives to aggregate and disseminate the information,” Ly stated. “But we’re also exploring how we can work with extension workers to effectively convey this information to farmers.”