Advances in artificial intelligence and biotechnology could soon allow the fragrance industry to reproduce scents and compounds from endangered plants without repeatedly harvesting them, according to scientists and biotechnology companies.
Many expensive perfumes rely on ingredients like agarwood, or oudh, a resin produced by wounded Aquilaria trees, which has led to illegal felling of wild trees and devastated populations. Now, companies are working on recreating such scents without harming the plants.
AI predicts and recreates scents
Alex Wiltschko, founder of Osmo, a Google Brain spin-off that has raised $130m to develop AI capable of predicting and recreating smells, said: "Being able to recreate the scent of an endangered plant would be a huge win for both the environment but also the brands." Osmo has recreated the scent of a rare tree from a piece of bark "the size of a finger", using a spectrometer to analyse the sample and AI to reconstruct the chemical formula.
BioHarvest Sciences says it has created a stable cell culture from an endangered south-east Asian fragrance plant, allowing its valuable compounds to be produced without cultivating or harvesting the original plant. The plant has not been named for commercial reasons, but BioHarvest has announced an agreement anticipating production of 20 tonnes of the fragrance composition, with limited production potentially beginning next year.
Conservationists sceptical
Zaki Rakib, BioHarvest's chief executive, said: "The challenge is that human demand can be effectively unlimited while biological supply is not. We believe biotechnology can help close that gap, not by replacing nature but by allowing us to use what nature has given us without continually putting the source under pressure."
But conservationists and perfumers are sceptical. Mandy Aftel, a natural perfumer and founder of the Aftel Archive of Curious Scents, said: "Calling this conservation is greenwashing. Making a synthetic version of an endangered plant's smell doesn't save the plant." She noted that producing a substitute did not stop people buying the original or address other causes of decline.
Rhian Smith of the Royal Botanic Gardens, Kew, agreed, pointing to the Aquilaria tree. AI could help design an alternative to oudh, she said, but wild-sourced material remained highly prized. "It doesn't completely take the pressure off wild plant species," she said. Wiltschko admitted that conservation was not "an explicit priority" for Osmo's work.
Limits of AI in scent creation
Synthetic perfume is not new; the industry has relied on synthetic ingredients for over a century, and machines have long identified molecules in scents. "What's changed is what happens after the data comes off the machine," Wiltschko said. "What's new is prediction." He claimed Osmo trained its AI on more than 5m human responses to smells, allowing it to predict how combinations of molecules will be perceived.
Other efforts include Christina Agapakis's work reconstructing genes from preserved flowers to produce fragrance compounds, and Future Society, which collected microbes from clouds on two flights, identifying 13 that produced 57 scent molecules, leading to a perfume launched this year. However, a flower's scent can contain hundreds of molecules and change based on plant part and growing conditions.
Agapakis said of her project: "The smell we got was this ghostly fragment of what had been lost." She could not recreate the living organism, soil, climate, season, or ecology that produced its scent. "What we have to remember is, ultimately, however powerful AI is, a smell is not simply a formula or dataset," she said.
