Digital technologies for agriculture represent an application domain of primary interest for Italy and for research at FBK. Italy is facing the challenge of a more efficient agriculture, able to improve the quality and value of products by improving environmental sustainability and enhancing local identities to the maximum extent. The application of Artificial Intelligence to environmental and climatic data, collected automatically in the field by machines, together with the company’s process data allow the development of solutions capable of promoting efficiency and productivity, improving the yield and sustainability of agricultural practices.
Strengths of the FBK modelFBK’s ten-year experience and its network of local, national and international partners make for an ideal innovation ecosystem to experiment with possible applications of AI in agriculture: from scientific research to technology transfer on sensors, remote sensing, IoT platforms and machine learning applications. Long-term collaborations with leading companies have allowed us to develop new Data Science and Deep Learning tools, IoT platforms and high-quality low- cost connected devices able to monitor the life cycle of crops and optimize management.
Featured projectsSAPIENCE The SAPIENCE project enables virtuous behavior in the agricultural sector by combining techniques for measuring and tracking the use of irrigation resources with incentive and reward tools. In particular, SAPIENCE promotes the efficient use of irrigation water, aiming to achieve a significant reduction (30% or more) compared to drip irrigation systems. This is possible thanks to monitoring based on IoT and blockchain technologies supported by a specific reward system that will encourage the virtuous behavior of the players. AI solutions for wine production In cooperation with CAVIT, FBK has developed a set of algorithms and systems to support winemakers during the fruit development phase up to the harvest. The system consists of different types of solutions to meet three different needs:
- Portable spectrometer with an AI system for in-field monitoring of oenological parameters (Brix and total acidity) during the pre-harvest phase;
- Deep Learning Model for early production estimation, analyzing images collected in the field via commercial smartphones;
- Deep Learning model for image segmentation and classification to recognize and quantify pests and optimize pesticide interventions.