Biologists have worked out how to “listen” to plants’ distress calls, paving the way for farmers to be sent an alert when crops are attacked by pests and diseases.
Scientists at Syngenta, an agricultural technology company in Basel, Switzerland, for the first time have used machine learning to decode the electrical signals emitted by plants.
And so far, the message that has come across most clearly is the equivalent of a plant dialling 999. Patrik Hoegger, head of the company’s insect control research group, said: “It’s the plant’s way of saying, ‘Ouch, I’m being hurt.’”
Botanists have known for more than a century that plants transmit electrophysiological signals between different parts of their structure. But until now these signals, which travel through the ion currents in tissue channels that transport water, minerals and nutrients throughout a plant, have been meaningless to humans.
The boom in machine learning and artificial intelligence capability, however, has transformed scientists’ ability to decipher and analyse huge amounts of data.
Anke Buchholz, a plant scientist at Syngenta, said: “Ten years ago we couldn’t have dreamed about doing something like this.”
By wiring up plants to electrical monitoring equipment in their huge glasshouses outside Basel, Buchholz and her team worked out they could start to process the data. And the plants were not keeping quiet. “A human cannot handle this amount of information,” she said. “We are getting 256 data points per second.”
Electrodes in soybeans monitor the plants’ response when they are threatened by stink bugs
SYNGENTA
When the plants had been wired up, the scientists experimented with exposing them to different stressors. In one experiment, the results of which are published in the Journal of Pest Science, they exposed tomato plants to microscopic nematode worms in the soil. In a second experiment, published in the Scientific Reports journal, they released a swarm of stink bugs among soybean plants.
By monitoring the electrical output from the plants and running it through their computer models, the team could spot the moment the plants came under attack.
This could be a vital early warning signal, Hoegger said, because in each of these cases it is almost impossible to detect pest damage until it is too late.
“Nematodes are pests in the soil so you don’t see them,” he said. “You only see the damage when you realise the yield is far lower than usual.”
• This woman can hear worms: listen to the sound of a healthy garden
Likewise, the damage caused by stink bugs — a pest which is common in the soybean farms of south and central America — is usually only detected about a week after they have attacked a plant, by which time it is too late.
Soybeans are a crucial crop, accounting for roughly half of the world’s plant-based protein. Yet 21 per cent of crops are lost each year due to pests and pathogens.
Buchholz said use of the new technology could help lead to more targeted, gentler pesticides. Current crop protection techniques take a carpet-bombing strategy: farmers blitz their fields with chemicals to combat any threat.
“At the moment we have a hard target,” Buchholz said. “The insects have to be dead to make sure they are not harming the crops.”
If farmers had an early warning about what was attacking their crops it could lead to better targeted pesticides
GETTY
But if farmers are able to tell from their monitoring equipment when a crop comes under attack — and from what species of insect — it might be sufficient to use far more specialised chemicals simply to deter the pests, or at least only harm the ones which are causing a problem. “This might give us a softer way of preventing insects from harming the crops,” said Buchholz.
That is a goal for the future. At the moment the scientists can only tell when a plant is under stress — not the particular pest that is attacking it. But Buchholz said it was a “medium term” target to be able to differentiate plants’ cries, telling apart the different insects, diseases or fungal infections that afflict them.
“We would like to build up a dedicated library,” she said. “That would be a very useful tool to have in our hands.”
Listening to plants is within scientists’ reach. Now, they just need to work out how to reply.