Artificial intelligence is not the scary, half-human half-robot movie character some might think it is, says Precision AI founder Daniel McCann.
“AI is just a data processing system that points out patterns in huge volumes of data and that’s it,” he said during a presentation at the virtual Canada’s Farm Show.
For agriculture, it represents the future.
McCann said he believes within the next 15 years common pieces of farm equipment, such as the broadcast sprayer, will become like a BlackBerry — still around, not too common and not too efficient.
But he said AI in agriculture is at an interim step along the way to that.
“The technology isn’t mature enough yet to get all the way, but we’re seeing incremental benefits,” he said.
As more AI is adopted on farms, the more its transformational power will be apparent. Its use will save money on chemical and fertilizer applications and address the labour shortage, he said.
AI on its own is one thing, but pairing it with robotics makes it tremendously powerful, McCann said.
“That’s when you can use it to automate difficult or menial tasks with a high degree of precision, often with a much higher degree of precision than humans are actually capable of processing,” he said.
He uses the example of a toddler looking at a picture of dogs. It takes only one dog of one species for the toddler to determine what a dog looks like.
“For artificial intelligence to have the same type of processing it takes 20 million images of different dog species, so there is a huge gap between what a human intelligence is and what an artificial intelligence is.”
People are already using AI in applications on their phones, for example. An app that allows you to take a picture of skin and analyze moles for cancer has just been released. AI is also responsible for the cat video recommendations people receive.
McCann said think about an acre of wheat with between one and 1.5 million plants on it. Humans don’t have the capability to look at each individual plant to see how it’s doing and predict crop yield.
But drones can do that by taking pictures of the field and using AI to process each one. This could help analyze soil moisture or determine where the weed pressure is.
Drones can determine which plant is a weed and which is crop. Specific weeds can be identified, and then where they are and how much chemical to apply. Farmers might not have to spray an entire field if there is only a weed problem in certain areas.
McCann said the possibilities of using AI data for more efficient farming are endless.
“I personally believe it’s one of the most transformative things to happen in agriculture in the last 100 years,” he said.
Satellite images will be able to predict drainage. Sensors in the soil and on tractors and combines will generate huge amounts of data that can be run through an artificial intelligence system to obtain meaningful information farmers can act on.
“That’s how AI is going to transform agriculture,” he said.
Soil health will benefit as fertilizers are applied more efficiently. McCann said fertilizer maps and spray maps can be loaded into machines to control application rates based on need.
He suggested the most interesting application will be in the area of labour as AI and robotics become part of equipment.
McCann said it’s an inevitable progression.
People used to get tools and build their own house. Then they realized they could hire someone to do it quicker and cheaper so they purchased services from different people.
The next level is the outcome model — going to a homebuilder and writing a cheque.
McCann said precision agriculture is like trying to sell outcomes to the farmer.
“Instead of selling you, for example, a sprayer that sits in your shed for six months out of the year they would want to sell you a field clear of weeds. The only way to achieve this level of maturity is through artificial intelligence,” he said. “You have to process enough data to be able to know how to be able to apply these types of chemical agents to a field to generate an outcome so that you as the farmer can actually just go and buy a field clear of weeds and the people already have enough data to know how to deliver that.”
For now, McCann said AI is still primitive. The utopia of running an entire farm on it is a ways off but innovators in ag tech are working on it.