Plant identification can be incredibly challenging for beginning botanists or even experienced plant people. There are tons of terms to learn and understand just to start identifying plants by leaves and other plant parts. Throw in a leafless winter, and it makes for a difficult skill to develop with confidence.

In recent years, photo-based smartphone applications have been developed to aid with plant identification in the field. These apps boast their accuracy, and many claim to provide identification for a wide array of species based on an image of the foliage. Do these apps work, and how accurate can they be?

A research paper published recently in the scientific journal, “Arboriculture and Urban Forestry,” explored the accuracy of photo-based plant identification apps. Researchers with the Rutgers Urban Forestry Program designed and implemented this study, which assessed the apps’ abilities to identify photos of 55 common trees.

For the study, experienced arborists photographed both bark and leaves of trees and submitted the photos to the six most downloaded plant identification apps based on downloads from the Apple App Store. The apps include iNaturalist, PlantNet, Leafsnap, PlantSnap, PictureThis and Plant Identification.

At least four images of both bark and leaves for each tree species were submitted to each app. Researchers observed and recorded the results. The apps use photo recognition software programmed to identify leaves and bark based on the common characteristics of these plant parts.

To me, it is extraordinary that these apps have the ability to process visual data and generate near-accurate results. As a trained botanist, I know that two leaves for the same tree can often vary.

While there is typically a recognizable pattern and distinctive characteristics common across all leaves on the same plant, certain species (typically within the same genus) can have similar leaf characteristics. This makes it possible for a single plant to have individual leaves in its canopy that are distinctive of its true species and other leaves that would lead you to believe it’s another, similar-looking species.

Knowledgeable botanists are aware of these nuances and take care to assess several leaves at differing locations within the canopy. However, beginners often make the common mistake of looking at one low-hanging leaf, which may or may not be the best example to observe. Due to instances like this, I have always discounted the use of plant identification apps and have not recommended them to beginners. However, some promising results were uncovered by Rutgers.

Each app makes suggestions, often several, for species-level identification of the plant in question. The study found while species-level identification by leaf pictures was not always the most accurate (83.9 percent to 40.9 percent) across all apps observed, genus-level identification by leaves was pretty good, reporting accuracies from 97.3 percent to 71.8 percent. Across all apps and all species, identification by bark pictures alone was not nearly as accurate.

For identification by leaves, the most accurate two apps were PictureThis (97.3 percent accurate to genus, 83.9 percent to species) and iNaturalist (92.3 percent accurate to genus, 69.6 percent to species). These results suggest that phone apps can help beginners rapidly arrive to a genus-level identification. With the aid of a good guidebook, beginners can quickly reach species-level determinations since the possibilities are narrowed down by the phone app.

While the Rutgers study presents some fascinating data, this research did not assess the community aspect that some of these apps provide. Several of the apps in this study also offer an option where users can ask the community of other app users to identify the plant in question.

I have found that community responses on these apps are typically highly accurate to the species level and often come from experts. So, when beginners can combine phone apps with other tools, such as community responses and the use of guidebooks or other reference materials, these applications have promising potential.