Scientists have trained anAIalgorithm to count the number of flowers on fruit trees using only smartphone images.

Researchers from Chile, Spain, and the UKs National Robotarium developed the algorithm.

The Robotarium is a centre forroboticsand AI based in Edinburgh, Scotland.

This AI algorithm counts flowers on trees to predict crop yields months in advance

The team looks to address a global problem.

Agriculture uses around 70% of the worlds freshwater andwastesalmost half of it.

Around 50% of the fruit and vegetables grown for human consumption are alsolost.

Siôn Geschwindt

The flower-counting AI could reduce this waste.

It could also boost farmers yields by improving their allocation of water and fertiliser.

40% off TNW Conference!

The team has already tested the AI at an orchard in Spain.

It predicted flower counts there with 90% accuracy.

Manual counts typically range from 50% to 70%, for comparison.

In September, the researchers will validate the AIs predictions against the real peach harvest.

Farming is one of the worlds oldest industries, but also one of theleast efficient.

Another startup, BelgiumsRobovision, has created a platform for managing AI-based vision systems on farms.

Story bySion Geschwindt

Sion is a freelance science and technology reporter, specialising in climate and energy.

Also tagged with