Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 12;9(5):290.
doi: 10.3390/biomimetics9050290.

Can Plants Perceive Human Gestures? Using AI to Track Eurythmic Human-Plant Interaction

Alvaro Francisco Gil  1   2 , Moritz Weinbeer  3 , Peter A Gloor  1
Affiliations

Can Plants Perceive Human Gestures? Using AI to Track Eurythmic Human-Plant Interaction

Alvaro Francisco Gil et al. Biomimetics (Basel). .

Abstract

This paper explores if plants are capable of responding to human movement by changes in their electrical signals. Toward that goal, we conducted a series of experiments, where humans over a period of 6 months were performing different types of eurythmic gestures in the proximity of garden plants, namely salad, basil, and tomatoes. To measure plant perception, we used the plant SpikerBox, which is a device that measures changes in the voltage differentials of plants between roots and leaves. Using machine learning, we found that the voltage differentials over time of the plant predict if (a) eurythmy has been performed, and (b) which kind of eurythmy gestures has been performed. We also find that the signals are different based on the species of the plant. In other words, the perception of a salad, tomato, or basil might differ just as perception of different species of animals differ. This opens new ways of studying plant ecosystems while also paving the way to use plants as biosensors for analyzing human movement.

Keywords: eurythmy; machine learning; plant action potentials; plant biosensors; plant–human interaction; signal processing.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Picture of one experiment performed at the Biodynamic Research Garden, Rheinau, Switzerland.
Figure 2
Figure 2
Measurement of voltage differences in lettuce and resulting measurement data.
Figure 3
Figure 3
Schematic representation of one measurement.
Figure 4
Figure 4
Histogram of plant electrical recordings by generation and plant.
Figure 5
Figure 5
Schematic display of automatic trimming of hand-labeled signals.
Figure 6
Figure 6
Two different waves from the dataset with their respective calculated flatness ratio metrics. (a) Normal wave, with all flatness values below the thresholds. (b) Outlier, with all values above the threshold. See the appendix for an explanation of the flatness ratio.
Figure 7
Figure 7
Eurythmy and control average electrical signals when eurythmy gestures were performed. Each line represents the mean of all recorded values for voltage changes over time associated with eurythmy recordings, and control recordings, respectively.
Figure 8
Figure 8
Confusion matrix for the lightGBM (lgbm) model between eurythmy and control.
Figure 9
Figure 9
Canonical representation of the average potential curves for each group, derived from resampled and averaged data. Each line represents the mean of all recorded values for voltage changes over time associated with gestures corresponding to the letters "A," "G," and "D," respectively.
Figure 10
Figure 10
Confusion matrix for the XGBoost (xgb) model between eurythmy letters (A-G-D).
Figure 11
Figure 11
Canonical representation of voltage curves for lettuce, tomato, and basil. Each line represents the mean of all recorded values for voltage changes over time associated with lettuce, tomato, and basil respectively.
Figure 12
Figure 12
Confusion matrix for the lightGBM (lgbm) model between lettuce, tomato and basil.
See this image and copyright information in PMC

References

    1. Darwin C. The Variation of Animals and Plants under Domestication. John Murray; London, UK: 1868.
    1. Bose J.C. The Nervous Mechanism of Plants. Longmans, Green and Co.; London, UK: 1926.
    1. Davies E. Plant Electrophysiology: Theory Methods. Springer; Berlin/Heidelberg, Germany: 2006. Electrical signals in plants: Facts and hypotheses; pp. 407–422.
    1. Stahlberg R. Plant Electrophysiology: Theory Methods. Springer; Berlin/Heidelberg, Germany: 2006. Historical introduction to plant electrophysiology; pp. 3–14.
    1. Trewavas A. The foundations of plant intelligence. Interface Focus. 2006;7:407–422. doi: 10.1098/rsfs.2016.0098. - DOI - PMC - PubMed

LinkOut - more resources