Cannabis (Cannabis sativa L.) is a dioecious plant that produces both male and female inflorescences. In nature, male and female plants can be found with nearly equal frequency, which determines species out-crossing. In cannabis farming, only female plants are preferred due to their high yield of cannabinoids. In addition to unfavorable male plants, commercial production of cannabis faces the appearance of hermaphroditic inflorescences, species displaying both pistillate flowers and anthers. Such plants can out-cross female plants, simultaneously producing undesired seeds. The problem of hermaphroditic cannabis triggered a search for analytical tools that can be used for their rapid detection and identification. In this study, we investigate the potential of Raman spectroscopy (RS), an emerging sensing technique that can be used to probe plant biochemistry. Our results show that the biochemistry of male, female and hermaphroditic cannabis plants is drastically different which allows for their confirmatory identification using a hand-held Raman spectrometer. Furthermore, the coupling of machine learning approaches enables the identification of hermaphrodites with 98.7% accuracy, whereas both male and female plants can be identified with 100% accuracy. Considering the label-free, non-invasive and non-destructive nature of RS, the developed optical sensing approach can transform cannabis farming in the U.S. and overseas.

Proper crop management requires rapid detection methods for abiotic and biotic stresses to ensure plant health and yield. Hemp (Cannabis sativa L.) is an emerging economically and environmentally sustainable crop capable of yielding high biomass. Nitrogen deficiency significantly reduces hemp plant growth, affecting photosynthetic capacity and ultimately decreasing yield. When symptoms of nitrogen deficiency are visible to humans, there is often already lost yield. A real-time, non-destructive detection method, such as Raman spectroscopy, is therefore critical to identify nitrogen deficiency in living hemp plant tissue for fast, precise crop remediation. A two-part experiment was conducted to investigate portable Raman spectroscopy as a viable hemp nitrogen deficiency detection method and to compare the technique’s predictive ability against a handheld SPAD (chlorophyll index) meter. Raman spectra and SPAD readings were used to train separate nitrogen deficiency discrimination models. Raman scans displayed characteristic spectral markers indicative of nitrogen deficiency corresponding to vibrational modes of carotenoids, essential pigments for photosynthesis. The Raman-based model consistently predicted nitrogen deficiency in hemp prior to the onset of visible stress symptoms across both experiments, while SPAD only differentiated nitrogen deficiency in the second experiment when the stress was more pronounced. Our findings add to the repertoire of plant stresses that hand-held Raman spectroscopy can detect by demonstrating the ability to provide assessments of nitrogen deficiency. This method can be implemented at the point of cultivation, allowing for timely interventions and efficient resource use.