Turning agrifood waste into sustainable protein with fermentation

Image: Freepik

19 January 2026 | Muriel Cozier

A team of researchers from the UK and Australia are collaborating on the development of an AI powered tool that could help cut food waste as well as improve food security. Led by the UK’s University of Leeds, which is collaborating with Australia’s national science agency, the Commonwealth Scientific and Industrial Research Organisation (CSIRO), the researchers are building a tool that will allow for the calculation of the optimal set of fermentation conditions to produce microbial protein for the lowest possible cost. 

Upcycling waste food to produce sustainable high-quality protein via fermentation allows for the production of ingredients that can be used in the manufacture of food, or to produce meat and dairy alternatives.

The researchers explain that with food waste being such a variable feedstock, the fermentation process is complex. That means, designing optimal fermentation and subsequent downstream processing requires a lot of decisions to be made on reaction inputs and variables. This increases the production time and the cost of any product, making adoption of such ingredients by the food sector challenging.
 
To tackle this problem, the research team says that their tool can calculate the optimal set of fermentation conditions to produce microbial protein for the lowest possible cost. The tool will provide “actionable insights into the type of yeast, fermenter and optimal process conditions to use, which will help industry to develop proteins tailored to their needs quickly and easily,” the team says. 
 
Nicholas Watson, professor of artificial intelligence in food, at the University of Leeds, said: “To truly impact global food security, upcycled protein can’t just be a niche alternative, it has to compete on price with what is already on the supermarket shelf.”
 
CSIRO says that in Australia more than seven million tonnes of food is wasted each year, representing one third of all food produced. The new project will cover three types of agrifood waste: vegetable crops that have been damaged or not picked; grain byproducts such as canola or brewer’s spent grain; and byproducts from cheese making. 
 
CSIRO project lead Kai Knoerzer said: “Globally billions of tonnes of nutrient rich material are currently being lost each year. Working with our colleagues internationally, this project will combine AI, fermentation science and real case studies to support industry to turn that waste into sustainable protein at scale.”
 
The project, which will run for two years, is supported by the Bezos Earth Fund’s AI for Climate and Nature Challenge. This is a $100 million initiative which is designed to harness AI in tackling climate change and biodiversity loss.  
Show me news from
All themes
from
All categories
by
All years
search by

Read the latest news