Ricerc@Sapienza

For countries whose economy relies significantly on agriculture, it is fundamental to quickly detect the outbreak of crop diseases and understand the dynamics of their propagation.
Nevertheless, especially in low-income countries, crop monitoring is still mostly left to a small number of insufficiently prepared extension workers, who perform manual and visual monitoring on site, gathering data with poor statistical reliability.
This is mostly due to the lack of skilled personnel, and of appropriate supporting infrastructure.

To face the above issues, we envision the use of a new pioneering network of flying monitoring drones to detect diseases and predict the speed and direction of their propagation while it is still in progress.

Supported by AI, the drones can detect field anomalies. Moreover, they can coordinate with each other to perform disease recognition at the desired level of fidelity, and forecast the direction and speed of the disease propagation.

Such a monitoring system will thus trigger prompt intervention to protect the smallholder farms not yet affected by the disease, to treat the affected plants when possible, and to enable protection policies to stop or mitigate the disease propagation, such as the creation of firewall lines and the adoption of pest control chemicals or medicines.

The availability of such a powerful tool, based on relatively cheap devices will ensure the adoption of pioneering technologies for food security, in areas where the local population is unprepared and poorly trained to recognize and face crop diseases, and where the economic growth of the country is slow.
Our proposed tools offer the prospect of early discovery of a spreading disease that will allow informed decision making by small farm holders, or by government offices in terms of pest and disease control interventions, as well as monetary investments in the most appropriate directions.