New flower-counting AI comes to the aid of fruit farmers

A new AI system could help farmers make their crop yields more efficient, sustainable, and profitable.

It uses images taken with just a standard smartphone to accurately estimate the number of flowers on a fruit tree.

It does this by recognising patterns and features, such as the edges and shapes of petals, even when they overlap or are partially obscured.

High accuracy

When tested on peach orchards in Catalonia, Spain, the AI predicted flower counts with 90% accuracy.

To compare, current manual methods, such as counting by eye or taking area samples, can have error rates of 30–50%.

Researchers say the system could provide more precise yield forecasts up to six months before harvest.

This could help growers optimise water use, allocate human and economic resources more efficiently, and better plan harvesting and distribution logistics.

Estimates suggest that, globally, agriculture uses 65% of the world’s fresh water, almost half of which is wasted.

Meanwhile, around 45% of fruit and vegetables produced for human consumption are lost or wasted every year across the global supply chain.

READ MORE: Parkside launches ‘game-changing’ Popflex lidding film

READ MORE: Blueberry growers harness renewable energy to boost yields

Expansion to other fruits

Researchers from the National Robotarium, the UK’s centre for robotics and AI based in Edinburgh, will validate the AI’s predictions against the actual peach harvest in September 2024. 

If proven effective, the approach could be adapted for other important crops like apples, pears and cherries, benefiting fruit growers in Britain, Europe and beyond.

The National Robotarium is part of the Data-Driven Innovation initiative, supported by £21 million from the UK Government and £1.4 million from the Scottish Government. 

The initiative aims to turn Edinburgh into the data capital of Europe and is part of the wider £1.5 billion Edinburgh and South-East Scotland City Region Deal.

Fernando Auat Cheein is an associate professor in robotics and autonomous systems at the National Robotarium. 

He said: “In countries all across the world, farmers often rely on manual methods to estimate their yields, which can have a significant error margin. 

“By leveraging the power of AI and the convenience of off-the-shelf technology like smartphones, our approach seamlessly integrates with traditional farming practices, making it easier for growers to embrace and benefit from innovative solutions without overhauling their existing methods.”

Tackling challenges

Researchers worked closely with peach farmers in Spain to understand the challenges they face.

“The farmers appreciated the simplicity and accuracy of the flower counting AI, noting its potential to help them make more informed decisions about crop management, such as targeted pruning and herbicide application,” Fernando said.

By focusing their efforts on the areas that were predicted to yield the most fruit, farmers were able to optimise their resources, reduce their environmental footprint, and maximise both the quantity and quality of their harvest.

The research project was developed by academics and researchers from the National Robotarium, the Advanced Center for Electrical and Electronic Engineering from Federico Santa Maria Technical University (Valparaiso, Chile) and Universidad Andres Bello (Chile).

Read more fruit news.