New AI tool predicts harvest time six months before the crop is ready

A new artificial intelligence (AI) system can be used to predict crop yields up to six months before harvest, researchers say.

The tool counts flowers on fruit trees, which could help farmers increase their crop yields and improve their allocation of resources such as water and labor, as well as plan harvests and distribution.

The system, developed by researchers at the National Robotarium in Edinburgh, can accurately estimate the number of flowers on fruit trees from photos taken with a standard smartphone.

It recognizes patterns and features, such as edges and shapes of petals.

Trials in peach orchards in Spain showed the system was 90 percent accurate in its estimates of flower numbers, compared to manual counts, which researchers say have error rates of between 30 and 50 percent.

“In countries around the world, farmers often rely on manual methods to estimate their yields, which can have a significant margin of error,” said Fernando Auat Cheein, associate professor of autonomous systems at the National Robotarium.

“By leveraging the power of AI and the convenience of commercially available technologies like smartphones, our approach seamlessly integrates with traditional farming practices, making it easier for growers to adopt and benefit from solutions innovative without overhauling their existing methods. »

Mr Cheein said that during the trial in Spain, farmers “appreciated the simplicity and accuracy of flower counting AI and its potential to help them make more informed decisions on crop management, such as targeted pruning and herbicide application.”

“By focusing their efforts on areas of the farm that are expected to produce the most fruit, farmers can optimize resources, reduce their environmental footprint and maximize both the quantity and quality of their harvest,” he said. he declares.

The researchers will then compare the AI ​​predictions with the actual peach harvest in September 2024.

If these measures prove effective, they believe this approach could be adapted to crops such as apples, pears and cherries, benefiting fruit growers in Britain, Europe and beyond.

According to researchers, agriculture uses about 65 percent of the planet’s fresh water, almost half of which is wasted, while each year about 45 percent of fruits and vegetables produced for human consumption are lost or wasted.

The research project was developed by academics and researchers from the National Robotarium, Federico Santa Maria Technical University and Andres Bello University in Chile.

The National Robotarium is the UK’s center for robotics and AI and is part of the Data-Driven Innovation initiative, supported by £21 million ($26.6 million) from the UK government and £1.4 million sterling from the Scottish Government.

Its researchers collaborate with industry partners to develop solutions to the most pressing challenges facing the agricultural sector, from improving crop yields and quality to reducing environmental impact and improving durability.

Updated: June 17, 2024, 11:01 p.m.