A spectroscopy and machine-learning method shows promise for tracing North…

Tracing the roots of illicit Cannabis: A machine learning-assisted ATR-FTIR proof-of-concept study for geographical origin classification.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy • • Highly Relevant
🤖

AI Summary

This proof-of-concept study asked whether ATR-FTIR spectroscopy combined with machine learning could classify the geographical origin of illicit cannabis. Researchers analyzed 200 female cannabis flower-top samples collected from four regions of North India, recording 1,000 spectral observations. The primary outcome was classification performance: among four models, an artificial neural network performed best during training, and the researchers also assessed its reliability with test data and unknown samples.

The spectra included signals associated with cannabinoids and other plant constituents. Across the models, principal component 3 contributed most to classification and was associated with plant materials including holocellulose, lignin, and pectin, as well as THCA and THC. The abstract reports no classification accuracy figures, so the size of the model’s performance cannot be assessed here. This is an abstract-based summary: as a proof-of-concept study on samples from four North Indian regions, it cannot establish how well the method would classify cannabis from other places or under broader forensic conditions.

💡 Key Findings

1
The study tested whether ATR-FTIR spectra and machine learning could classify the geographical origin of cannabis flower samples from four North Indian regions.
High
95%
2
Among four evaluated models, the artificial neural network performed best during training; the abstract gives no accuracy figures.
High
95%
3
Principal component 3 contributed most to classification across the models and was associated with plant constituents including THCA and THC.
High
90%
4
The work is a proof of concept; the abstract does not establish how reliably the approach would classify cannabis beyond the sampled regions and reported validation data.
High
95%

📄 Original Abstract

Cannabis remains one of the most commonly trafficked and seized illicit drugs around the globe. The growing number of cannabis seizures has created an increasing demand for analytical methods able to determine the geographical origin of seized material rapidly and reliably. Existing approaches are often destructive, require extensive sample preparation, and have limited applicability to Indian cannabis. To address these limitations, the present study explored Fourier-transform infrared spectroscopy in attenuated total reflectance sampling mode (ATR-FTIR) combined with machine learning (ML) approaches for the geographical classification of cannabis samples collected from North India. A total of 200 female cannabis flower-top samples were collected from four distinct geographical regions and 1000 spectral observations were recorded using ATR-FTIR spectroscopy. The spectra obtained presented characteristic absorption bands related to cannabinoids, flavonoids, cellulose, hemicellulose, lignin, and other phytochemical constituents. Then, dataset was reduced using principal component analysis (PCA) and subsequently used to train four ML models. Among the models evaluated, the artificial neural network (ANN) exhibited the best classification performance during the training phase. Its reliability was further validated internally using test data and externally using unknown data. Further, PC3 was the most contributing component to the classification across all models and was associated with holocellulose, lignin, pectin, THCA, and THC. The proposed work has a strong potential for forensic investigations, especially for drug trafficking and identification of cannabis origin in illicit market.

Explore More Research

Stay informed about the latest cannabis science.

Your stash, decoded.