Researchers are using artificial intelligence to develop a new app that warns farmers of fungal diseases that could destroy potato crops.
Welsh scientists say the app allows farmers to use their phones to detect late blight before they become visible to humans.
A research team at Aberystwyth University said the disease is responsible for 20% of economic losses in potato crops worldwide and £3.5 billion.
He added that early diagnosis will increase productivity, reduce farmers' costs and reduce their dependence on pesticides that are harmful to the environment.
The DeepDeTect project uses machine learning to provide farmers with accurate, location-specific disease diagnosis with their smartphones.
“By integrating farmer feedback from the start, we ensure that this technology is based on real needs and challenges,” says Akpokodje, a lecturer in computer science at Aberystwyth University.
The technology has the potential for wider applications across other crops, he said.
The purpose of this project is to reduce the environmental and financial burden of preventive spraying. Researchers said that the current cost Welsh farmers up to £5.27 million a year.
Potatoes are a globally important crop, with over 17,000 hectares in Wales dedicated to potato farming.
The team plans to create an AI-driven prototype using image datasets of healthy, sick potato leaves.
They then refine the model and ultimately the team hopes to create a nationwide early warning system for potato blight, as the technology could expand to other crops and regions in the future.
“Potatoes are the fourth most important staple food crop in the world, and production is essential to increase the world's population,” said Aiswarya Giriya of the Institute of Biological, Environmental and Rural Sciences at Aberystism University.
“So potato devastation is not merely agriculture, it's a matter of food security.”
