Africa’s food production systems are increasingly challenged by numerous threats, including weather shocks, plant disease and pest outbreaks, the COVID-19 pandemic, and other health emergencies. The challenges posed by these crises relate to not only the extent and complexity of the disruptions but also the difficulty in identifying and tracking them in real time. It is challenging, even in normal times, to have complete and accurate information on cropping activities and gathering reliable information is even more difficult during emergencies. When crises strike there are additional difficulties in knowing how growing conditions will affect crop production or whether farmers will have access to the inputs and labor they need. Typically any impacts on harvested quantities are determined at the end of the growing season thus leaving farmers to play catch up in dealing with a crisis and its impacts. Without the ability to accurately and timely predict impacts on agricultural production, a weather shock or a health crisis can easily to turn into a food crisis.
The lack of information about growing conditions can be overcome by using today’s digital technologies. Remotely sensed data enables real time tracking of changes in vegetation cover, weather data, and other parameters related to cropping activities. Recent developments in machine learning and computer modeling make it possible to track and predict crop production using remotely sensed data. The benefits go far beyond the ability to overcome the obstacles to data gathering during crises. The many weaknesses that hamper access to good quality agricultural statistics can also be overcome using the same digital technologies, from measuring arable land, planted areas, crop yields to the spatial distribution of harvested quantities.
Scientists at AKADEMIYA2063 have developed the Africa Agriculture Watch (AAgWa), a web-based platform that is linked to a technical model that employs cutting edge machine learning techniques and remotely sensed data to predict agricultural yields and production levels of several crops across Africa. Therefore, AAgWA provides valuable information to support crisis management, monitoring, and mitigation efforts in local communities.
Forecasts for Decision-Making
Harness cutting-edge predictive modeling technologies such as machine learning techniques to provide forecasts and reduce uncertainties in decision-making processes in African food production systems.
Remote Sensing Data for African Agriculture
Overcome the agricultural statistics data gap in Africa by the use of remote sensing data through satellite images.
Web-based tool for accessibility
Facilitate the access and use of remote sensing products and forecast maps by embedding the ready-to-use AAgWa outputs in a web-based tool.
Racine LyDirector, Data Management, Digital Products and Technology
Babacar CeesaySenior Manager, Information Systems
Khadim DiaSenior Associate Scientist
Tidiane BaSenior Specialist, Visual Design and Production