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.
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
📄
Original Abstract
Related Research
Similar Studies
More THC research papers you might find interesting.
Small lab study finds cannabis affected simulated driving and confidence
A lab method measures 17 cannabinoids across five hemp product types
A single-center study finds varied care and no recurrence in follow-up
Explore More Research
Stay informed about the latest cannabis science.