THIS CONTENT IS BROUGHT TO YOU BY NTNU Norwegian University of Science and Technology - read more
Can artificial intelligence help save nature?
AI and eight million old plant specimens reveal how the climate is changing nature across large parts of the world.
The Royal Botanic Gardens in Kew, England, recently published a report on the state of the world’s plants and fungi.
It examines what digitisation and AI are doing for botany and nature management. The report includes contributions from 400 researchers in 40 countries, including researchers from NTNU.
“For hundreds of years, naturalists have collected plants and fungi, pressed and dried them, so that they could be preserved for the future in herbariums around the world. In recent years, more and more specimens have been photographed and made available online,” says James Speed.
He is a professor of plant ecology at the NTNU University Museum and one of the contributors to the report.
“More than 145 million plants and fungi preparations have been digitised worldwide, from over 170 institutions in 40 countries. This opens up completely new opportunities for research,” he says.
20 years of work completed in a single week
“What’s so exciting is that we’re taking collections that have existed for centuries, combining them with machine learning and AI technologies that are barely five years old, and we can then answer big, important questions about nature,” says David Williamson.
He is a researcher in machine learning for natural history at the NTNU University Museum.
“Machines can’t do the work of biologists, but they can help experts analyse datasets that would previously have taken a lifetime,” he says.
Together with James Speed and botanists from the Trondheim herbarium, he trained a machine learning model to recognise whether plants were in bloom in digitised herbarium specimens.
The model was used on eight million preserved specimens. These were collected from all over the world and represent a total of 200,000 species.
“By way of comparison, the machine here took one week to do something that would have taken a human about 40,000 hours,” says Williamson.
To put that number in perspective, 40,000 hours equal about 20 working years.
Researchers surprised by changes in the tropics
“These analyses showed that global flowering times have shifted by an average of 2.5 days per decade over the past century,” says Speed.
Flowering has shifted both earlier and later, and the differences are greatest in tropical areas.
The greatest temperature increases due to climate change tend to be in the far north, so researchers were surprised to learn that the most dramatic flowering changes were in the tropics.
“In the tropics, flowering is more related to precipitation. In a changing climate, the rainy season can come earlier, later – or not at all,” says Speed.
When flowering times change, a mismatch can arise between flowering plants and pollinating insects. This can in turn have ripple effects, for example on insect-eating birds and food production.
“We are going to investigate these consequences in more detail in a new project,” Speed reveals.
The effects of climate change on flowering time are only one of the questions that digital herbarium specimens can answer. The same methods can be used in the fight against species extinction.
Tools in the fight against extinction
Millions of plants and fungi are still unknown to science. At the same time, species extinction and climate change are accelerating. Some species are disappearing faster than researchers can document them.
Fungi are the basis for almost all life on Earth. But more than 90 per cent of species are still unmapped. Only 1,000 plant species have officially been declared extinct, even though the actual number is likely to be much higher.
AI and machine learning cannot solve these problems. What they can do is give researchers mapping tools they have never had before.
By making millions of old herbarium specimens searchable and machine-readable, researchers can now identify which parts of the world and which groups of species we know too little about. Fieldwork can then be prioritised where it is needed most.
Statistical models can also calculate the probability that a species is extinct, rather than simply not having been found again. AI can recognise unknown species in digitised collections and flag them for experts, speeding up the naming process.
“You’d still need taxonomists to check those names were accurate and that there were no mistakes. But with less time spent on identifying the more common 90 per cent of species, we’d have more time to get on and describe the unknown species and to do things to conserve the threatened species,” says Martin Cheek.
He is a researcher and taxonomist at the Royal Botanic Gardens in Kew.
Machines need people
Before we get completely carried away by technological optimism, it is worth considering that less than 16 per cent of the world’s herbarium specimens are digitally accessible.
The biggest gaps are found in countries with rich biodiversity, where collections are understaffed, poorly documented, and not connected to global databases.
“While AI is a useful tool for researchers, it doesn’t think for us. Our models are only as good as the data they are trained on. Experts need to be involved at every step – from asking the right research questions to validating the model design and interpreting the results," says Williamson.
He adds that new technologies underscore how important the work done by people in museum collections really is.
Reference:
Antonelli et al. State of the World's Plants & Fungi (PDF), Research report, Royal Botanic Gardens, Kew, 2026.
———
Read the Norwegian version of this article on forskning.no
More content from NTNU:
-
Elderly people living at home have less control, not more
-
Researchers are looking for solutions that will encourage people to leave their cars at home
-
Trade unions help raise wages and reduce the gender pay gap
-
How microplastics affect carbon uptake in the ocean
-
This period has been referred to as Europe's homosexual breakthrough
-
These apprentices have a greater chance of success
