Know Your Lavender Oil

October 3, 2023
3 minute read
George Hill
Sagitto Ltd

There are many species of Lavandula worldwide, but most Lavandula essential oils are extracted from either Lavandula angustifolia ('Lavender') or Lavandula x. intermedia ('Lavandin'). Lavandula angustifolia tends to yield less oil and therefore usually sells for a higher price. This has led to reports of substitution with other, lower-cost species of Lavandula.

One of the most frequently mentioned adulterant is lavandin (Lavandula × intermedia) oil. However it can be difficult for consumers to tell the difference between lavender and lavandin.

Lavender or Lavandin?

Lavender oils tend to have a more delicate, floral aroma when compared to lavandin oils. The latter are more pungent due to their relatively high concentrations of cineol (also known as eucalyptol), camphor, and borneol.

"The difference between the two oils is easily detectable by scent, however, when blended together, the sharper tones of lavandin are diluted, thus, making it difficult to detect by scent alone. At approximately $38 AUD/kg for lavandin essential oil compared to $251 AUD/kg for lavender essential oil, the incentive to adulterate oil is high considering the lack of regulation and the low probability of the adulterant being identified." [5 ]

For example here are the concentrations of  three distinguishing components for some Australian essential oils: four lavender cultivars (Avice Hill, Bee, Maillette, and Swampy) and three lavandin cultivars (Grosso, Seal, and Sumian), measured using gas chromatography.

1-8-cineole in lavender oil
1-8-cineole (cineole is another name for eucalyptol, the main ingredient in eucalyptus oil.)
Camphor in lavender oil
Hexyl isobuterate and Camphor
Borneol in lavender oil

To differentiate between lavender and lavandin oils, we don't need to go to the trouble of using expensive and time-consuming gas chromatography equipment. Sagitto has taken NIR spectra from 57 different lavender oils sourced from reputable New Zealand lavandula oil producers and built a very accurate machine learning model that does the same job.

testing essential oils with miniature NIR spectrometer
Testing essential oil with a Sagitto miniature NIR spectrometer

With just a few drops of oil in a glass cuvette, placed on one of Sagitto's miniature NIR instruments, in a few seconds we have a report on our phone that shows whether the oil is lavender or lavandin, or if its even a pure essential oil. (Cheaper oils are often adulterated with a carrier oil.)

Munstead i a cultivar of Lavandula angustifolia
Within seconds we can see the result on our phone
An example of false labelling of lavender oil
This oil is is probably adulterated with a carrier oil

We are able to distinguish between lavender and lavandin with a very high degree of accuracy. And we automatically check for anomalous samples - those that look very different from genuine Lavandula oils.

Accurate classification of lavender species using machine learning
Sagitto model accurately distinguishes lavender from lavandin

How Does This Work?

Sagitto's machine learning algorithms can detect the subtle differences in the absorbance spectra of different lavender oils. We use these differences to distinguish between lavender oil and lavandin oil, and between individual cultivars too.

Relative importance of parts of NIR spectrum for classifying lavender
Differences in the absorbance spectra allow us to readily distinguish between true lavender oil, and lavandin oil

Distinguishing Different Cultivars

We can extend this technique to individual cultivars just as easily too, provided they are cultivars that the model has seen before.

Accurate classification of lavender cultivar using NIR and machine learning
NIR can be used to distinguish between individual lavender cultivars
Example of a lavender sample that it not labelled true to type
An example of an oil that is not true to label

What We See With NIR

The reason that we can discriminate between Lavandula species, and cultivars within these species, is that each essential oil sample has its own unique chemical composition which in turn influences the way that the oil absorbs light in the near infrared region.

NIR absorbance spectra for lavender essential oil
Lavandula angustifolia "Avice Hill" has a very different NIR absorbance spectrum to Lavandula x. intermedia "Super".

Composition Of Lavender and Lavandin Oils Using NIR

For several years, Sagitto has helped its customer Manuka Biologicals to accurately quantify the chemical composition of manuka oil using infrared spectroscopy. We know that near infrared spectroscopy, when coupled with sophisticated machine learning and good quality training data from gas chromatography analyses, is a powerful tool for those wanting to ensure that they consistently produce and/or sell high quality essential oils.

While we do not have access to GC data for the 57 New Zealand lavender and lavandin oils that we have collected, Sofia Lafhal and her colleagues at Aix Marseille Université, France have shown that the main compounds in lavender and lavandin oil (such as linalool and linalyl acetate) can be very accurately measured using near infrared spectroscopy.


Like any natural product, there are many sources of variability in essential oil quality: geographical location, seasonal variation, time of harvest, and differences in oil extraction and post-harvest storage can all have an effect on the final oil composition.

Producing high quality lavender and lavandin is challenging enough for genuine producers, without the added complexity of combating oil adulteration. Near infrared spectroscopy is a valuable tool in ensuring that consumers are receiving oil that is true to label.


1. Chris Burder, formerly owner of Stone Rise Farms, Victoria, Australia, for providing the GC analyses of his lavender oils

2. Sofia Lafhal, Pierre Vanloot, Isabelle Bombarda, Jacky Kister, Nathalie Dupuy. Chemometric analysis of French lavender and lavandin essential oils by near infrared spectroscopy. Industrial Crops and
Products, 2016, 80, pp.156 - 164. ff10.1016/j.indcrop.2015.11.017ff. ffhal-01451404f

3. American Botanicals Council, Botanical Adulterants Prevention Bulletin, Adulteration of English Lavender (Lavandula angustifolia) Essential Oil, Sept 2020

4. Capetti, Francesca & Marengo, Arianna & Cagliero, Cecilia & Liberto, Erica & Bicchi, Carlo & Rubiolo, Patrizia & Sgorbini, Barbara. (2021). Adulteration of Essential Oils: A Multitask Issue for Quality Control. Three Case Studies: Lavandula angustifolia Mill., Citrus limon (L.) Osbeck and Melaleuca alternifolia (Maiden & Betche) Cheel. Molecules. 26. 5610. 10.3390/molecules26185610.

5. Beale, D.J.; Morrison, P.D.; Karpe, A.V.; Dunn, M.S. Chemometric Analysis of Lavender Essential Oils Using Targeted and Untargeted GC-MS Acquired Data for the Rapid Identification and Characterization of Oil Quality. Molecules 2017, 22, 1339.

6. last but not least - the many New Zealand lavender growers from whom we have bought oil samples

Subscribe to Sagitto's Blog

Get industry insights that you won't delete, straight in your inbox.
We use contact information you provide to us to contact you about our relevant content, products, and services. You may unsubscribe from these communications at any time. For information, check out our Privacy Policy.
George Hill
Sagitto Ltd
Sagitto's founder, George Hill, first started working with artificial intelligence during the 1980s, while developing 'expert systems' within Bank of America in London. On returning to New Zealand, he undertook part-time study with the University of Waikato's Machine Learning Group while working for Hill Laboratories, a well-known New Zealand commercial testing laboratory. This led to the formation of Sagitto Limited, dedicated to combining the power of artificial intelligence and machine learning with spectroscopy.

More news

Vendor Lockin

You Should Be Free To Leave

We believe that our customers should subscribe to our services willingly, because of the value that they receive and not because they are locked in to using us. That is why we take particular care to provide a smooth pathway, should our corporate customers decide to no longer use Sagitto's services.

Read Article
Data Science

Benchmark Against Machine Learning Models

The success of generative AI applications such as ChatGPT and DALL-E has increased public awareness of the power of artificial intelligence software. Sagitto's Benchmarking Service allows users of infrared spectroscopy instruments to benchmark their current models against models generated by machine learning.

Read Article
Data Science

Outlier Detection - Sorting The Sheep From The Goats

Outlier detection is an important step in preparing spectroscopy data for machine learning models. Hotelling's T2 and Q-Residuals are two outlier detection methods commonly used in chemometrics. However, Sagitto has found that they need to be used with caution to avoid discarding unusual but valid data.

Read Article