“Can we put microphones underground to listen to earthworms as they move?” This is not a question many people would think to ask. But it is one of several that Quentin Geissmann, Assistant Professor at the Centre for Quantitative Genetics and Genome Research at Aarhus University, is setting out to answer. Starting in 2024, his ambitious, five-year project combines biology, computer programming and artificial intelligence (AI) and is funded by the Novo Nordisk Foundation Research Leader Programme.
It has long been known that earthworms are one of nature’s specialised decomposers, recycling organic matter and returning nutrients to the soil. In that way, they are both a useful model and a pivotal actor when transitioning to a more sustainable, circular type of agriculture – a change that is widely considered essential to avoid further depletion of arable lands and help ensure future food security.
But, according to Quentin Geissmann, we just do not know enough about earthworms to understand precisely how they can help this transition.
“We know earthworms are good, but we don’t have high resolution data on worm activity,” he says. “If you want to understand what happens to earthworms when you harvest or plant, the subtle ways they change their behaviours, we need data at a higher frequency. We need to know what they are doing, but also when and where.
“Most of the methods available so far have been essentially digging the soil – you go around with a shovel, you dig and then you count. I think we can switch gear a little bit and try to develop methods that not only give us more data, but a more comprehensive picture.”
The Emerging Investigator grant of DKK 9.5 million will enable him and his team to build up that picture by looking at – and listening to – earthworms in brand new ways.
According to Quentin Geissmann, it can be tricky to find funding for research such as this, where the potential applications are numerous, but may not come to fruition for 15 years or so. The Research Leader Programme grant hits “a sweet spot between basic research and applied research,” he says. “It enables something that I doubt would have been possible with many other funding schemes.”
From insects to AI and earthworms
Quentin Geissmann began life in France, becoming interested in insects from a young age. While studying biology at university, a lecture in computer programming opened his eyes to the untapped potential of combining these fields. He got hooked and later developed a PhD project in the UK using programming and 3D printing to study sleep in fruit flies. Next was Vancouver, where he used digital methods to monitor biodiversity.
“Like many people, I grew more interested in applying my work as a scientist to more mission-driven things – so not just looking at sleep in fruit flies, which we can do in fifty years if we want – but addressing more immediate problems.”
This project is a natural next step – applying remote sensing and machine learning to a creature that is ubiquitous (an average of 20 earthworms are found per square metre globally, scientists estimate), pivotal in humanity’s food supply, and yet “that people have not paid too much attention to,” according to Quentin Geissmann.
Cameras, microphones and sensing boards
First, he and his team plan to develop machine learning tools that can take images of and identify earthworm species, speeding up a process that currently relies on experts looking at worms under a microscope.
Then comes the remote sensing work – using cameras above ground, and electronic sensing boards and microphones below ground – to gather detailed information about earthworm activity. When do earthworms leave their burrows and come to the surface? Do they always return to the same burrow? How often and how much do they eat? Do they interact with other worms as they move around?
Lastly, Quentin Geissmann and his team will investigate whether and how earthworms and plants interact, an area where there is currently very little knowledge.
“Earthworms don’t just live in soil,” he says. “They navigate through a forest of roots, so some of them have probably evolved ways to communicate with plants. It could be that when plants face a root pathogen, they call – indirectly or not – an earthworm that will eat the dead root and restrict the pathogen’s progression.”
AI is involved at every stage, from a deep-learning algorithm that will identify earthworm species from cylindrical images and a camera system designed to capture foraging earthworms to an algorithm used to distinguish earthworms from plant roots in terraria.
Another tool in the farming toolbox
He hopes that this research will enable humans to protect earthworms’ ability to preserve and restore soils, while also learning how to actively utilise their agricultural services.
Farmers could use the new knowledge about earthworm behaviour to make decisions about when to plough or till their fields, so fewer worms are killed in the process, Quentin Geissmann explains. They could introduce plants to their land that interact with earthworms in ways useful to sustainable agriculture, or worms themselves could be bred and put in the field, just as we do now with natural enemies of pests.
“We are already moving towards recording everything on farms, and using prediction models, satellite images and drones to monitor plant health, pests and soil moisture,” he says. “Monitoring life underground is just one more tool to help us manage farming a little better.”
DKK 361 million awarded
The Foundation’s Research Leader Programme funds daring and innovative project ideas that may lead to significant scientific breakthroughs. The five-year grants are awarded to talented researchers at different stages of their careers.
A total of DKK 361 million has been awarded to 37 researchers in the 2023 round. Quentin Geissmann is one of 16 Emerging Investigators to receive an award, granted to promising researchers who want to establish or are in the process of establishing their own research group and research leader profile.
In total, the Foundation has now awarded more than DKK 2 billion to more than 200 researchers through the Programme since it was established in 2018.
Read more here: https://researchleaderprogramme.com/
Christian Mostrup, Head of Press, Novo Nordisk Foundation, email@example.com, +45 3067 4805