Fig 1.
Workflow for testing AI-based plant identifications across applications.
The diagram summarizes the stepwise procedure used to assess identification suggestions obtained from iNaturalist and PlantNet across different locations settings and plant parts.
Table 1.
Summary of the models used and relevant parameters to evaluate the taxonomic accuracy score in response to the effects tested.
Table 2.
P-values of the differences between the factor levels and the reference factor level of the tested effects on the taxonomic accuracy assessment obtained through clmm2 modelling.
Fig 2.
Predicted probabilities of established and outsider plants according to taxonomic accuracy and location using iNaturalist.
Location parameters: No Location (NL), Ontario (ON) and Ottawa (OTT). The difference in outsider plants between No Location and Ontario or Ottawa is significant (p < 0.001).
Fig 3.
Predicted probabilities of established plants according to taxonomic accuracy, family, status, and tool type interaction.
Tool type: iNaturalist (iNat) and Plant Net (PN). The difference between Poaceae and Asteraceae is significant (p < 0.01) and between PlantNet and iNaturalist (p < 0.05 in the family modelling; p < 0.01 in the distribution status modelling).
Table 3.
Error rate and standard error of outsider plants according to location using iNaturalist (n = 402). The errors at every level of the taxonomic accuracy assessment were combined to calculate the overall error rate and standard error.
Fig 4.
Predicted probabilities of established plants according to taxonomic accuracy and plant parts using iNaturalist.
The difference between pictures with only leaves and with only an inflorescence(s) is significant (p < 0.05).
Fig 5.
Example of iNaturalist suggestions when location is not used and used as an input.
A) Includes suggestions returned when location is not inputted. B) Includes suggestions returned when Ottawa is inputted as the location. C) includes suggestions returned from selecting “Include suggestions not expected nearby” below in B. iNaturalist image of Echium plantagineum was used and we can observe that this species is not among the suggestions until we selected “Include suggestions not expected nearby” when the location is used as an input. Observation 127042112, by brianvanhezewijk [Brian Van Hezewijk], 19/Jul/2022, license is CC BY-NC 4.0. This identification was confirmed by author (AC) as Echium plantagineum with a dried collected specimen sent to the CFIA by Brian in 2024.
Table 4.
Summary of addressed biases and their effect on the identification suggestions made by applications.