Mario Koeppen

These days, complex food supply chains, characterized by the production, distribution, transport, processing, retail and consumption of food get more and more entitled to various risks and hazards: contamination, domino effects, contamination propagation (incl. virus spread), resource depletion, origination and quality disputes. Here, farming is not only farm production of food at some location, but has to be seen by its effects on the whole chain. This is a challenge that needs proper reflection in any concept of Precision Agriculture. Here, we want to discuss the various stages and the related technology challenges.

The novel viewpoint here is to start on the documentation of the whole system. Bullet items of such a documentation are: new sensors data logs, incl. polarization, thermal, acoustic, multi-spectral imaging and wearables (monitor farmer condition and status) integration, incl. hierarchical classification and prediction tasks; security, esp. the tracking of ingredients mixtures, or the special multi-factor and small scale modality of blockchain technology. Further on, we need to explore new computational intelligence solutions for the task of retrieval of data to give it into the hand of consumers, a broad avenue for fuzzy information processing. Novel optimization approaches are needed for the interplay of the various optimization modalities of the food system: farmers' "look after things" as a correction-driven cognitive ability of humans brought into the AI domain, scheduling with respect to distribution and transport stage, efficiency and non-physical optimization for the processing and manufacturing stage, and the price-driven retail and consumption stage. All those tasks have been studied in perfect isolation so far, but to keep them in a global balance poses new requirements on optimization algorithms flow. We might take inspiration from the microbiome and how it achieves its task to keep an organism up and running. As a last step, how about moving the food system from a chain to a circle and base it on circular economy, to tackle the problem of incentives driving the system and avoid future harm caused by the classical domino effect?

The whole story has just opened its first chapter. But we have already promising technology at hand, incl. Big Data and IoT, global communication, low-cost sensors, and Computational Intelligence. Those can surely support to move away from the isolated efficiency race per food system stage to the safety-oriented, open, holistic and versatile documentation point of view towards the design and conception of a future smart farming system.