From Australia AI revolution in fruit fly detection

25 Jun 2024
771

According to researcher Maryam Yazdani, the new technology based on artificial intelligence could facilitate access to exporting countries.  

Australian researchers have tested a new way to detect fruit flies in cherries and other fruits using an optical scan programmed by artificial intelligence. The project by the CSIRO (Commonwealth Scientific and Industrial Research Organisation), led by entomologist Maryam Yazdani, aims to make detection more efficient and effective. 

"Many horticultural companies use optical scanning as a key component of the quality sorting process," Yazdani told Fruitnet. "What we tried to do [with our research] was to develop a specific imaging system for pest detection that could be integrated into the existing optical sorting systems at packing centers." 

Yazdani said she hopes this system can open up market access to countries currently closed to Australian exporters due to the potential fruit fly risk. Currently, Australia uses final treatments such as fumigation and manual inspections to manage fruit fly infestation risks for fruit exported internationally and for internal transport between states.  

"Australia already has very strong security measures," Yazdani said. "But this emerging technology can provide additional tools to border security regulators to minimize the risk of pest transport." Indeed, Yazdani sees the potential of optical scanning as an alternative to fumigation.  

"Fumigation is quite costly and has already been banned in many countries," she said. "We may not have access to some countries in the coming years, so we really need an alternative to fumigation."

The optical scanning technology captures high-resolution images of the fruit as part of the sorting process. From the images, the artificial intelligence program can detect infestations, including recently laid eggs inside the fruit, which can be removed through existing selection technologies within the warehouse. 

The program works by referencing previous images of infestations and matching the defect signs in new fruits. According to Yazdani, the team generated more than 40,000 images over three years to "train" the AI program.

"When we have high-quality data, the artificial intelligence model we are developing is more accurate," Yazdani said. "So far, the detection model we have developed for fruit fly damage in cherries has achieved about 95% accuracy." 

Read the full article: Fruitnet
Image: Koppert


Cherry Times - All rights reserved  

What to read next

Varietal innovation, patents and brand strategies, the winning trio for the modern cherry industry

Varieties

30 Jan 2025

For an in-depth look at the topics of varietal innovation and modern commercial development strategies for new cherry varieties, Stefano Lugli of Cherry Times interviewed James Calissi, owner of Calissi Farm, a company specialising in nursery and management of new varieties.

Varieties, exports and production: Turkish focus in USDA report

Production

12 Sep 2024

Turkey’s cherry production for the 2024/25 marketing year (MY) is expected to decrease compared to last year's record, but it will still be the third-largest ever. Despite the decline in production, cherry exports are projected to reach an all-time high.

In evidenza

Brassinolide protects “Tieton” cherries from cold damage during storage in China

Post-harvest​

26 Jun 2025

A study from Yantai, China shows that brassinolide application improves the storage of “Tieton” cherries, significantly reducing cold damage, weight loss, and degradation of visual and nutritional quality of the fruits during prolonged cold storage conditions.

Meda cherries tested in 12 European countries, first fruits harvested in the Netherlands

Varieties

26 Jun 2025

Meda cherries gain traction across Europe: trials in 12 countries, first harvest in the Netherlands, and over 1,200 hectares assigned worldwide. The project spans USA, Chile, South Africa and China, focusing on quality, earliness, innovation and agronomic sustainability.

Tag Popolari