Refine
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- deep learning (2)
- - (1)
- Automated monitoring (1)
- Chiroptera (1)
- F1 score (1)
- ROXAS (1)
- artificial intelligence (1)
- bat conservation (1)
- camera trap (1)
- carbon balance (1)
Institute
Publisher
- Wiley (2)
- Frontiers Media S.A. (1)
- Nature Publishing Group (1)
Plant roots influence many ecological and biogeochemical processes, such as carbon, water and nutrient cycling. Because of difficult accessibility, knowledge on plant root growth dynamics in field conditions, however, is fragmentary at best. Minirhizotrons, i.e. transparent tubes placed in the substrate into which specialized cameras or circular scanners 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. Our minirhizotron data come from various wetlands on organic soils, i.e. highly heterogeneous substrates consisting of dead plant material, often times mainly roots, in various degrees of decomposition. This may be seen as one of the most challenging soil types for root segmentation in minirhizotron images. RootDetector showed a high capability to correctly segment 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 more than 13-times higher root length/cm2 per image compared to expert analysts. CNNs such as RootDetector provide a reliable and efficient method for the detection of roots and root length in minirhizotron images even from challenging field conditions. Analyses with RootDetector thus save resources, are reproducible and objective, and are as accurate as manual analyses performed by human experts.
BatNet: a deep learning-based tool for automated bat species identification from camera trap images
(2023)
Automated monitoring technologies can increase the efficiency of ecological data collection and support data-driven conservation. Camera traps coupled with infrared light barriers can be used to monitor temperate-zone bat assemblages at underground hibernacula, where thousands of individuals of multiple species can aggregate in winter. However, the broad-scale adoption of such photo-monitoring techniques is limited by the time-consuming bottleneck of manual image processing. Here, we present BatNet, an open-source, deep learning-based tool for automated identification of 13 European bat species from camera trap images. BatNet includes a user-friendly graphical interface, where it can be retrained to identify new bat species or to create site-specific models to improve detection accuracy at new sites. Model accuracy was evaluated on images from both trained and untrained sites, and in an ecological context, where community- and species-level metrics (species diversity, relative abundance, and species-level activity patterns) were compared between human experts and BatNet. At trained sites, model performance was high across all species (F1-score: 0.98–1). At untrained sites, overall classification accuracy remained high (96.7–98.2%), when camera placement was comparable to the training images (<3 m from the entrance; <45° angle relative to the opening). For atypical camera placements (>3 m or >45° angle), retraining the detector model with 500 site-specific annotations achieved an accuracy of over 95% at all sites. In the ecological case study, all investigated metrics were nearly identical between human experts and BatNet. Finally, we exemplify the ability to retrain BatNet to identify a new bat species, achieving an F1-score of 0.99 while maintaining high classification accuracy for all original species. BatNet can be implemented directly to scale up the deployment of camera traps in Europe and enhance bat population monitoring. Moreover, the pretrained model can serve as a baseline for transfer learning to automatize the image-based identification of bat species worldwide.
Abstract
Root phenology influences the timing of plant resource acquisition and carbon fluxes into the soil. This is particularly important in fen peatlands, in which peat is primarily formed by roots and rhizomes of vascular plants. However, most fens in Central Europe are drained for agriculture, leading to large carbon losses, and further threatened by increasing frequency and intensity of droughts. Rewetting fens aims to restore the original carbon sink, but how root phenology is affected by drainage and rewetting is largely unknown.
We monitored root phenology with minirhizotrons in drained and rewetted fens (alder forest, percolation fen and coastal fen) as well as its soil temperature and water table depth during the 2018 drought. For each fen type, we studied a drained site and a site that was rewetted ~25 years ago, while all the sites studied had been drained for almost a century.
Overall, the growing season was longer with rewetting, allowing roots to grow over a longer period in the year and have a higher root production than under drainage. With increasing depth, the growing season shifted to later in time but remained a similar length, and the relative importance of soil temperature for root length changes increased with soil depth.
Synthesis and applications. Rewetting extended the growing season of roots, highlighting the importance of phenology in explaining root productivity in peatlands. A longer growing season allows a longer period of carbon sequestration in form of root biomass and promotes the peatlands' carbon sink function, especially through longer growth in deep soil layers. Thus, management practices that focus on rewetting peatland ecosystems are necessary to maintain their function as carbon sinks, particularly under drought conditions, and are a top priority to reduce carbon emissions and address climate change.
The recent developments in artificial intelligence have the potential to facilitate new research methods in ecology. Especially Deep Convolutional Neural Networks (DCNNs) have been shown to outperform other approaches in automatic image analyses. Here we apply a DCNN to facilitate quantitative wood anatomical (QWA) analyses, where the main challenges reside in the detection of a high number of cells, in the intrinsic variability of wood anatomical features, and in the sample quality. To properly classify and interpret features within the images, DCNNs need to undergo a training stage. We performed the training with images from transversal wood anatomical sections, together with manually created optimal outputs of the target cell areas. The target species included an example for the most common wood anatomical structures: four conifer species; a diffuse-porous species, black alder (Alnus glutinosa L.); a diffuse to semi-diffuse-porous species, European beech (Fagus sylvatica L.); and a ring-porous species, sessile oak (Quercus petraea Liebl.). The DCNN was created in Python with Pytorch, and relies on a Mask-RCNN architecture. The developed algorithm detects and segments cells, and provides information on the measurement accuracy. To evaluate the performance of this tool we compared our Mask-RCNN outputs with U-Net, a model architecture employed in a similar study, and with ROXAS, a program based on traditional image analysis techniques. First, we evaluated how many target cells were correctly recognized. Next, we assessed the cell measurement accuracy by evaluating the number of pixels that were correctly assigned to each target cell. Overall, the “learning process” defining artificial intelligence plays a key role in overcoming the issues that are usually manually solved in QWA analyses. Mask-RCNN is the model that better detects which are the features characterizing a target cell when these issues occur. In general, U-Net did not attain the other algorithms’ performance, while ROXAS performed best for conifers, and Mask-RCNN showed the highest accuracy in detecting target cells and segmenting lumen areas of angiosperms. Our research demonstrates that future software tools for QWA analyses would greatly benefit from using DCNNs, saving time during the analysis phase, and providing a flexible approach that allows model retraining.