Truace
Subscribe

using AI and biotechnology to reproduce scents from endangered fragrance plants to reduce wild harvesting

Source article: Making scents: could AI help perfumers take pressure off endangered plants?

Many of the world’s most expensive perfumes begin with a wounded tree. When some Aquilaria trees are damaged, they produce a dark, fragrant resin that becomes agarwood, or oudh – an ingredient so valuable that wild trees have been illegally felled in its pursuit. The result has devastated wild Aquilaria populations. But what if perfumers could create the smell without cutting down the tree? With the help of AI, scientists are learning to predict how molecules that have never been made will smell, reconstructing…

By the Truvace desk2 min read1 sourceJournalismTRV-2026-1301· cite & verify
Making scents: could AI help perfumers take pressure off endangered plants?
Trace impact readingNegative state
P 56The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.

Both sides are scored from claims and sources, not community votes.

G 51The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.

In brief

By October 2026, fragrance biotech firms were using AI to recreate scents from endangered plants from minimal material. Osmo reported rebuilding a rare tree's scent from a finger-sized bark sample after spectrometer analysis, while BioHarvest Sciences said it had a stable cell culture of an unnamed south-east Asian fragrance plant and anticipated 20 tonnes of composition with limited production potentially beginning next year.

The development matters because high-value ingredients like agarwood or oudh have driven illegal felling and devastated wild Aquilaria populations, and a lab alternative could lower direct harvesting pressure. Whether that translates into conservation remains uncertain, as perfumers and botanists warn that synthetic versions do not automatically curb demand for wild material and that commercial incentives, not conservation, are driving the work.

Main points

  1. Osmo, a Google Brain spin-off that raised $130m, says it trained AI on more than 5m human responses to smells to predict how molecule combinations will be perceived.
  2. BioHarvest Sciences reports a stable cell culture from an unnamed endangered south-east Asian fragrance plant and an agreement anticipating 20 tonnes of composition with limited production potentially beginning next year.
  3. Conservationists note wild Aquilaria trees have been illegally felled for oudh resin, devastating wild populations, and that wild-sourced material remains highly prized even when alternatives exist.

The gain

AI trained on millions of human smell responses can predict and reconstruct fragrances from tiny samples, enabling lab production of compounds from endangered plants without repeated harvesting.

The problem

Recreating endangered plant scents with AI and biotechnology risks greenwashing because synthetic versions do not save the species or eliminate demand for wild-harvested material.

The rundown

The piece describes a shift from traditional molecule identification to AI prediction: Osmo uses a spectrometer to analyse a tiny bark sample, then its model reconstructs the chemical formula and predicts perceived scent. BioHarvest pursues a parallel biotech route, growing plant cells in culture rather than cultivating or harvesting the source plant.

Skepticism centers on market behavior and motives. Natural perfumer Mandy Aftel and Kew's Rhian Smith argue substitutes do not address other drivers of decline and wild oudh remains prized. Osmo's founder acknowledged conservation was not an explicit priority, and BioHarvest has not named its target plant for commercial reasons.

Sources

  1. JournalismThe Guardian2026-10-06

The debate