New AI model developed at Western detects strawberry diseases, takes aim at waste

Joshua Pearce and Soodeh Nikan investigate strawberries in the agrivoltaic agrotunnel at the Environmental Sciences Western Field Station (Source: Jeff Renaud/Western Communications)

Research from Western University could help farmers get out of a jam by using artificial intelligence (AI) and camera monitoring to enhance strawberry cultivation.

A new paper produced by local researchers aims to use machine learning to predict ripeness and detect diseases early.

The hope is that the findings of John M. Thompson Chair in Information Technology and Innovation at Western Engineering Joshua Pearce, electrical and computer engineering professor Soodeh Nikan, and their collaborators will help extend the growing season of strawberries in Canada.

They managed to increase the accuracy of their study by monitoring their strawberries in a controlled environment – using indoor hydroponics, and grow lights.

“We have greatly increased accuracy in detecting different diseases and also sensing the brightness of the strawberries, which is crucial for understanding the quality of the crop and determining the best times to pick,” said Nikan.

Their computer system achieved nearly 99 per cent accuracy in predicting ripeness and classifying diseases.

Joshua Pearce and Soodeh Nikan investigate strawberries grown under an agrivoltaic installation at the Environmental Sciences Western Field Station (Source: Jeff Renaud/Western Communications)

What does this mean for the consumer? The hope is that models like the one produced at Western could help with your grocery bill.

“Reducing waste and the cost of food is obviously a big issue these days. Like everyone, I am always surprised when I go to grocery store and see the price of fresh fruits and vegetables,” said Nikan. “When choosing projects, I usually look for something that is safety critical or a societal need. With my experience in other applications, I jumped at the chance to apply my knowledge and expertise to food security.”

The team worked to make the model free, and easy to apply, with the hope that more farmers will choose to integrate it into their agricultural practice.

“The software is completely free and open-source and farmers of any type are free to download it and then adapt it to their needs,” said Pearce. “They may prefer to have the AI system send them an email or ping their phone when they detect disease or even forward an image of a specific plant that is ready to pick. The software is wide open to make it your own.”

What’s next for the team? They hope to implement their software outdoors in a less controlled environment – possibly using drones to monitor outdoor fields.

One day, a flying robot may just tell a farmer which field is ready when.