Agri Kultuur December / Desember 2018 - Page 31

conditions. These are then used to refine the data collected by sensors on the ground. It’s precise data collection without the thousand- dollar price tag. To transmit this data, FarmBeats is experimenting with using TV white space (unused spectrum between stations) instead of Wi-Fi, an option which is both cheap and abundant in developing regions. Once this data has been gathered, it is important to make sure it is available to small farmers in an open and democratic way. Programs like the CGIAR Platform for Big Data in Agriculture, which leverages the work and financing of multiple partners including the World Bank, have been set up to make datasets created by these innovative methods freely available to all. In Kenya, for example, where no robust data on the state of water resources in the Sondu-Miriu River basin exists, researchers have tested an approach to crowdsource it from citizens. Three water-level gauges were erected with signs that explained the project and asked passers-by to send measurements from the gauges through text messages. The data they received was cross-checked with much more expensive automatic gauging stations nearby and was found to be highly accurate. AgriKultuur |AgriCulture Elsewhere in Africa, free AI-powered apps are helping farmers detect pest and disease outbreaks in cassava. The app known as Nuru was designed by Penn State University in collaboration with CGIAR and Google using TensorFlow, an open source software for object recognition. It was crafted by taking 11,670 photos to create 2,756 images of leaves. After experts diagnosed the diseases, the photos were organized into a database which was used to train the software using machine learning to recognize the symptoms of cassava pests and diseases. The app is user-friendly, and farmers or extension agents simply point their smartphone camera at several cassava leaves and Nuru responds with a diagnosis. It can also be used offline, which is important in remote farm communities. Datasets that will inform the future of farming and protect food supplies into the future are growing. If they can be made available to all types of farmers, from large to small, rich and poor, we can catalyse an information revolution that will transform our global food system for the better. Juergen Voegele is Senior Director of the Food and Agriculture Global Practice at the World Bank and Chair of the CGIAR System Council. This post first appeared on AgriPulse. NOVEMBER 29, 2018 copyright 31