Canadian firm Resson is which is using imagery analytics to help deliver an increase in crop yields for companies such as McCain

“We’re going from precision agriculture to decision agriculture. And we’re trying to drive that revolution,” states Giri Baleri, VP for marketing at Resson, a university spin out from New Brunswick in Canada. Resson uses imagery combined with farm data to provide a range of analytics to growers.

One goal, he explains, is to detect issues like disease and pests, and preferably before they arrive.

Often there’s no rain during an entire summer, so you have no option but to pump water

Resson has been working with potato chip producer McCain to improve its growers’ harvests. Thanks to machine learning, its systems can diagnose the presence of viruses and pests, such as the beetles that eat potato foliage and so dent crop quality. This year it will have a limited commercial roll out with potato farmers across more than 10,000 acres in eight different geographies, and separately with a spinach grower in Arizona.

Water is also a target. “Often there’s no rain during an entire summer when plants are growing and ripening, so you have no option but to pump water, which costs money both for energy management and water rights,” says Baleri.


Resson is helping potato farmers diagnose viruses and pests. (Credit:Julia Sudnitskaya/Shutterstock)

 

Resson has been working with potato growers in the US and Canada, and in California’s Salinas Valley on a moisture assessment module for their valuable baby spinach and soft fruits crops. Thermal imagery gives a relative water index across a field, which can be correlated with soil moisture readings. Trials with tomato crops are about to begin.

The company has almost 50 people working in engineering and image analytics. Image collection costs are coming down all the time, especially with drones, says Baleri. The data itself provides valuable opportunities for research and development. Analytics costs vary but Baleri argues that $20-30 an acre for a crop value of over $1,000 an acre is a small price if they deliver an 8-10% increase in yield. On top of that, avoiding the application of fertiliser across an entire field can cut costs by more than 50%.

Angeli Mehta is a former BBC current affairs producer, with a research PhD. She now writes about science, and has a particular interest in the environment and sustainability. @AngeliMehta

This is part of our in-depth briefing Future of Farming. See also:

Future Farming: Pastures new for big data

From vertical farms to new proteins: innovating to feed the planet

A sea change in the way we farm fish

Can agri-tech sow a green revolution for India’s poorest farmers?

 

 

McCain  machine-learning  agri-tech  precision agriculture 

comments powered by Disqus