As good as human experts in detecting plant roots in minirhizotron images but efficient and reproducible: The Convolutional Neural Network “RootDetector”

Abstract

Plant roots influence many ecological and biogeochemical processes, such as carbon, water and nutrient cycling. Because of difficult accessibility, knowledge on plant root dynamics in field conditions, however, is fragmentary at best. Minirhizotrons, i.e. transparent tubes placed in the substrate into which specialized cameras are inserted, facilitate the capture of high-resolution images of root dynamics at the soil-tube interface with little to no disturbance after the initial installation. Their use, especially in field studies with multiple species and heterogeneous substrates, though, is limited by the amount of work that subsequent manual tracing of roots in the images requires. Furthermore, the reproducibility and objectivity of manual root detection is questionable. Here, we use a Convolutional Neural Network (CNN) for the automatic detection of roots in minirhizotron images and compare the performance of our RootDetector with human analysts with different levels of expertise. The minirhizotron data stem from various wetland types on organic soils. RootDetector showed a high capability to correctly segmenting root pixels in minirhizotron images from field observations (F1 = 0.6044; r² compared to a human expert = 0.99). Reproducibility among humans, however, depended strongly on expertise level, with novices showing drastic variation among individual analysts and annotating on average almost 3-times higher root length/cm² per image compared to expert analysts. Analyses with RootDetector save resources, are reproducible and objective, and are as accurate as manual analyses performed by human experts.

Code and data availability

The authors state RootDetector is supplied as usable code on GitHub, with the Data Accessibility section giving the repository URL, which matches an allowed URL.