Using AI to minimise overproduction and food waste
Of the millions of tonnes of food that end up in landfill every year, around 30% comes from the food production and processing stage, with around 52% accumulating in domestic households and 18% at the retail level.
In the Resource-efficient Intelligent Foodchain (REIF) project, the Fraunhofer Institute for Casting, Composite and Processing Technology IGCV collaborated with 30 partners to look at ways to reduce food waste by implementing AI into the food processing ecosystem.
Artificial intelligence can be a valuable asset. Cheese, bread, meat and other food products can be efficiently produced using data-based algorithms. Machine learning methods could be used to optimise sales and production planning as well as process and plant control systems.
Minimising overproduction and avoiding waste
There are various causes for avoidable waste, ranging from overproduction, to fluctuations in raw materials’ quality, to the food failing to fulfil specific aesthetic requirements.
The REIF team focused on dairy, meat and bakery products, with waste occurring on these products mainly because they can spoil quickly.
“Two aspects are key to significantly reducing food losses in these sectors — minimising overproduction and avoiding waste,” said Patrick Zimmerman, a scientist at Fraunhofer IGCV and member of the consortium.
Zimmerman, fellow researcher Philipp Theumer and five other colleagues began to analyse how a company’s internal potentials, such as in plant and machinery or production planning and control, can be optimised to reduce waste using AI methods.
“We apply AI to the entire value chain, especially in the production facilities. To do that, we adapt and select the algorithms that are suitable for the respective application,” Zimmerman said.
“We look at the predictability and controllability in all areas — from production on the farm to sale in the supermarket — to optimise their potential.”
“Overproduction and waste can be avoided by making targeted forecasts on food requirements, improving the predictability and controllability of the value creation processes and reducing quality-related food loss,” Theumer added.
The potentials for the implementation of AI are highly diverse. Zimmermann explains using a meat mixer as an example.
“The temperature and duration of the mixing process influences the expiry date of meat products. If we use AI algorithms to minimise the amount of energy admitted to the mixing process, we can extend the expiry date, which in turn optimises the selling time in the supermarket and reduces food losses.”
At a system level, the highest amount of food waste occurs at power-up. This is because the optimum parameters have to be identified first, and therefore waste is produced in the meantime.
“As an example, we are applying intelligent sensors and self-learning AI algorithms to perfect the foaming process during the production of cake bases at the first attempt,” Zimmermann said.
Linked information for all steps in the food chain
In the long term, the REIF project partners are looking to establish an IT ecosystem and set up a virtual marketplace.
In the future, the researchers predict companies will provide the AI algorithms they implemented to all participants on this platform. Another aim is to network the data of all companies involved in the project to enhance the added value within the food industry’s complex value network.
“One company’s expertise can be transferred to another organisation. The more data is made available, the better the AI model can be trained,” Zimmermann said.
The online marketplace is where the project partners can swap their data. Ultimately, production companies can better control their manufacturing processes by benefiting from sales figures’ sales forecasts. The data collected by supermarkets will be included in the forecasts.
Zimmermann said if the researchers bring together a range of factors like customer behaviour, inventory levels and expiry dates, they could make dynamic price adjustments on specific products in supermarkets.
“The continuous, daily price adjustment will avoid the drastic price slashing we are used to seeing shortly before the expiry date and prolong the selling time. Consequently, a product is more likely to be bought before it’s passed for disposal and the overall profit also increases,” said Zimmermann, explaining the principle of dynamic price adjustment.
This locks in maximum profit for the retailer while reducing waste and overproduction. The entire delivery chain benefits from the idea of sharing information, which also includes external data.
“If the weather report is good, supermarkets sell a lot of barbecue meat. Meat producers can adjust their slaughter volume accordingly and, vice versa, run-down production in poor weather,” said Zimmermann, explaining the IT ecosystem concept. And the end customer would also benefit: in poor weather, the price of barbecue meat could be reduced at an earlier time, saving it from sitting on the shelf. Prediction systems such as these could also be offered over the online platform.
The project partners are currently in the concept phase, with the first practical tests set to start soon in 2021.
Why do the largest nuts rise to the top? This discovery has the potential to lead to better...
Supply chains are changing at a breakneck pace. Before you decide to change, check it has...
Why ingredient origin is key to gaining consumer trust.