Data sharing remains a major hindering factor when it comes to adopting emerging AI technologies in general, but particularly in the agri-food sector. Protectiveness of data is natural in this setting; data is a precious commodity for data owners, which if used properly can provide them with useful insights on operations and processes leading to a competitive advantage. Unfortunately, novel AI technologies often require large amounts of training data in order to perform well, something that in many scenarios is unrealistic. However, recent machine learning advances, e.g. federated learning and privacy-preserving technologies, can offer a solution to this issue via providing the infrastructure and underpinning technologies needed to use data from various sources to train models without ever sharing the raw data themselves. In this paper, we propose a technical solution based on federated learning that uses decentralized data, (i.e. data that are not exchanged or shared but remain with the owners) to develop a cross-silo machine learning model that facilitates data sharing across supply chains. We focus our data sharing proposition on improving production optimization through soybean yield prediction, and provide potential use-cases that such methods can assist in other problem settings. Our results demonstrate that our approach not only performs better than each of the models trained on an individual data source, but also that data sharing in the agri-food sector can be enabled via alternatives to data exchange, whilst also helping to adopt emerging machine learning technologies to boost productivity.

How will artificial intelligence (AI) affect EU farmers? Bernard Ader, vice president of Copa-Cogeca, the united voice of European Farmers and Agri-cooperatives, answers Future Farming's questions. "It is essential for cooperatives and their farmer-owners to clearly understand the potential benefits and risks involved." What can European farmers expect from EU policies on AI? And in which areas does AI benefit farmers?

We are not aware of any concrete examples of AI already being used in farming practice, but the introduction of artificial intelligence provides the power to process huge amounts of data, pooling, and exchanging information with multiple data sources. It also provides decision support systems for complex choices that farmers and their cooperatives need to make. This gives farmers and their cooperatives a powerful tool to yield significant gains in terms of efficiency and productivity. It will be key to handle essential repetitive and diverse agricultural tasks such as weeding, harvesting crops, or milking cows. The same goes for the processing facilities for packaging logistics handled by our cooperatives. Artificial Intelligence also has a positive impact on working conditions, as it helps optimise the labour process and helps in accompanying farmers which can be significant for our sector. The same thing goes for farm and enterprises safety. We see that artificial intelligence can also support us in overcoming these huge problems. Additionally, AI can support us in tackling environmental and climatic challenges, especially in reducing the impact on the environment, reducing our carbon-footprint, and improving the functioning of the value chain. Agri-food cooperatives increasingly face the challenge of sustainable production. We are investing to improve the scope of innovations, preserve the integrity of the ecosystem, and improve the use of natural resources.

The AIC 2019 conference will focus on the increasing impact of artificial intelligence (AI) and robotics on the agri-food sector in Canada. As the agri-food supply chain evolves, AI and robotics will have a crucial impact on Canada's agri-food sector's capacity to adapt, compete and lead. Panels and presentations at AIC 2019 will focus on understanding the potential and the challenges posed by AI and robotics.