How artificial intelligence is helping make food production smarter
Food production is a complex process involving the careful monitoring and management of raw materials, supply chains, market prices and much more besides. Access to smart data enables food producers to plan intelligently and to optimize their production processes allowing them to produce the required quantities more cheaply and in a more environmentally friendly way. But this data can also be used to create additional revenue streams for producers – something that will be demonstrated at this year’s digital edition of Hannover Messe by members of a research consortium led by Professor of Business Informatics Wolfgang Maaß of Saarland University and the German Research Center for Artificial Intelligence (DFKI). In their ‘Evarest’ research project, the team turns proprietary data into a commodity that can be traded securely without disclosing any intellectual property or trade secrets.
What is next year’s harvest of cocoa beans or strawberries going to be like? When should we place an order and how much should we buy? How many sausages will be sold in November? How are commodity prices for grain, olive oil or meat going to develop and what quantities are going to be available and when? Food producers who have reliable answers to these questions can anticipate future demand and plan their production capacity more precisely. This can mean, for example, controlling production volumes so that they avoid overproduction at certain times of the year. A research consortium led by Wolfgang Maaß, Professor of Business Informatics at Saarland University, is showing how smart data can be used by food producers to yield reliable business forecasts.
‘Food production generates vast amounts of data, much of which has so far gone unused. That data represents unemployed capital. Using our data platform we can identify and establish relationships between production data sets. Once these data sets have been linked, analysed and evaluated, they can provide concrete recommendations for action whenever key production decisions need to be made,’ explains Wolfgang Maaß. While the individual data sets are essentially just columns of numbers and of little predictive value, when taken together this vast database can offer valuable operational insights. ‘The point of the exercise is not to disclose legitimately confidential industrial secrets or the operational know-how that makes a product unique. The data we use is anonymized operational data of the sort that accrues during production, such as sensor data, statistical information or data on quantities or volumes,’ says Maaß.
He sees huge potential in this data, not least how it can be used to combat overproduction and to help achieve climate goals. ‘Food production generates almost one third of global greenhouse gas emissions. At the same time, millions of tons of food are destroyed every year. That damages the climate and results in higher costs. Data-driven predictive production planning offers producers the opportunity not only to invest in their public image, save costs and generate revenue through data production, but also to protect the climate,’ explains Professor Maaß.
