Scalable Data Flow Management for Smart Farming Digital Twins
summary
Claims a working interoperability stack that feeds actionable digital twins to reduce chemical use (aligned with EU targets of 50% pesticide and 20% fertilizer cuts by 2030). Architecture uses retrofitted autonomous tractors with RGB and stereo cameras plus Edge AI (weed/pest/nitrogen/canopy detection), a cloud digital twin running WOFOST-style simulations, and a data hub built on Orion Context Broker and NGSI-L with the Smart AgriFood vocabulary; prototype pipeline is deployed in Horizon 2020 Smart Dropless pilots in Lithuania and Spain for wheat and apple orchards, with pilots validating end-to-end data flow rather than final yield reductions.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:53Smart farming interoperability
- 3:59Interoperability explained
- 6:07Smart Droplets project
- 8:15Actionable digital twins
- 11:24Autonomous data collection
- 15:57System interoperability
- 17:26Choosing agricultural ontologies
- 20:57NGSI-LD interoperability
- 24:26Use case walkthrough
- 26:13Conclusion
related talks
18mThe Future of Agriculture: Empowering Farmers with Data & Analytics
01h 15mFrom Food Commons to Data Spaces Shaping Data Governance...
25mFrom seed to store: AI to optimize the indoor farms of the future
30mDataOps for digital twins
30mPanel: Data-Driven Sustainability
33mLearning to Scale Agile-DevOps for Agricultural R&D
20mChampioning modern science workflows to benefit dairy farmers
16mSyngenta’s cloud journey to a decision science–based R&D
