Smart agriculture monitoring
Riaan Wolhuter, Department of Electrical & Electronic Engineering and Department of Agrisciences, Stellenbosch University, South Africa
Nathalie Mitton, research team FUN, Inria
The proposed research entails the development of a flexible, rapidly deployable, biological/agricultural data acquisition platform and associated machine learning algorithms. It seeks to create advanced agricultural monitoring and management techniques for better natural resource management and smart farming decision making. A first objective is to create an advanced, flexible wireless sensor network for wide area agricultural data measurement and the forwarding thereof to a central monitoring centre.
A second objective is to adapt current machine learning and pattern recognition algorithms to obtain an area wide and in depth view of crop and soil conditions to identify and enable optimal crop management and harvest conditions. These algorithms typically utilise and explore the interdependence of different parameters and their locality variability to obtain a statistically much more reliable view of trends and overall conditions. This could be of enormous value in presenting early warning signs of disease and other unwanted conditions. Finally, pilots will be deployed in both France and South Africa focusing on two main cultures: potato crop and vineyards.
Key words: wireless sensor networks, smart agriculture, machine learninge