An official website of the United States government
Abstract Mountain meadows are an essential part of the alpine–subalpine ecosystem; they provide ecosystem services like pollination and are home to diverse plant communities. Changes in climate affect meadow ecology on multiple levels, for example, by altering growing season dynamics. Tracking the effects of climate change on meadow diversity through the impacts on individual species and overall growing season dynamics is critical to conservation efforts. Here, we explore how to combine crowd‐sourced camera images with machine learning to quantify flowering species richness across a range of elevations in alpine meadows located in Mt. Rainier National Park, Washington, USA. We employed three machine‐learning techniques (Mask R‐CNN, RetinaNet and YOLOv5) to detect wildflower species in images taken during two flowering seasons. We demonstrate that deep learning techniques can detect multiple species, providing information on flowering richness in photographed meadows. The results indicate higher richness just above the tree line for most of the species, which is comparable with patterns found using field studies. We found that the two‐stage detector Mask R‐CNN was more accurate than single‐stage detectors like RetinaNet and YOLO, with the Mask R‐CNN network performing best overall with mean average precision (mAP) of 0.67 followed by RetinaNet (0.5) and YOLO (0.4). We found that across the methods using anchor box variations in multiples of 16 led to enhanced accuracy. We also show that detection is possible even when pictures are interspersed with complex backgrounds and are not in focus. We found differential detection rates depending on species abundance, with additional challenges related to similarity in flower characteristics, labeling errors and occlusion issues. Despite these potential biases and limitations in capturing flowering abundance and location‐specific quantification, accuracy was notable considering the complexity of flower types and picture angles in this dataset. We, therefore, expect that this approach can be used to address many ecological questions that benefit from automated flower detection, including studies of flowering phenology and floral resources, and that this approach can, therefore, complement a wide range of ecological approaches (e.g., field observations, experiments, community science, etc.). In all, our study suggests that ecological metrics like floral richness can be efficiently monitored by combining machine learning with easily accessible publicly curated datasets (e.g., Flickr, iNaturalist).
more »
« less
Using Convolutional Neural Networks to Efficiently Extract Immense Phenological Data From Community Science Images
Community science image libraries offer a massive, but largely untapped, source of observational data for phenological research. The iNaturalist platform offers a particularly rich archive, containing more than 49 million verifiable, georeferenced, open access images, encompassing seven continents and over 278,000 species. A critical limitation preventing scientists from taking full advantage of this rich data source is labor. Each image must be manually inspected and categorized by phenophase, which is both time-intensive and costly. Consequently, researchers may only be able to use a subset of the total number of images available in the database. While iNaturalist has the potential to yield enough data for high-resolution and spatially extensive studies, it requires more efficient tools for phenological data extraction. A promising solution is automation of the image annotation process using deep learning. Recent innovations in deep learning have made these open-source tools accessible to a general research audience. However, it is unknown whether deep learning tools can accurately and efficiently annotate phenophases in community science images. Here, we train a convolutional neural network (CNN) to annotate images of Alliaria petiolata into distinct phenophases from iNaturalist and compare the performance of the model with non-expert human annotators. We demonstrate that researchers can successfully employ deep learning techniques to extract phenological information from community science images. A CNN classified two-stage phenology (flowering and non-flowering) with 95.9% accuracy and classified four-stage phenology (vegetative, budding, flowering, and fruiting) with 86.4% accuracy. The overall accuracy of the CNN did not differ from humans ( p = 0.383), although performance varied across phenophases. We found that a primary challenge of using deep learning for image annotation was not related to the model itself, but instead in the quality of the community science images. Up to 4% of A. petiolata images in iNaturalist were taken from an improper distance, were physically manipulated, or were digitally altered, which limited both human and machine annotators in accurately classifying phenology. Thus, we provide a list of photography guidelines that could be included in community science platforms to inform community scientists in the best practices for creating images that facilitate phenological analysis.
more »
« less
- PAR ID:
- 10395101
- Date Published:
- Journal Name:
- Frontiers in Plant Science
- Volume:
- 12
- ISSN:
- 1664-462X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Summary Plant phenology, the timing of recurrent biological events, shows key and complex response to climate warming, with consequences for ecosystem functions and services. A key challenge for predicting plant phenology under future climates is to determine whether the phenological changes will persist with more intensive and long‐term warming.Here, we conducted a meta‐analysis of 103 experimental warming studies around the globe to investigate the responses of four phenophases – leaf‐out, first flowering, last flowering, and leaf coloring.We showed that warming advanced leaf‐out and flowering but delayed leaf coloring across herbaceous and woody plants. As the magnitude of warming increased, the response of most plant phenophases gradually leveled off for herbaceous plants, while phenology responded in proportion to warming in woody plants. We also found that the experimental effects of warming on plant phenology diminished over time across all phenophases. Specifically, the rate of changes in first flowering for herbaceous species, as well as leaf‐out and leaf coloring for woody species, decreased as the experimental duration extended.Together, these results suggest that the real‐world impact of global warming on plant phenology will diminish over time as temperatures continue to increase.more » « less
-
Abstract Climate change is shifting the environmental cues that determine the phenology of interacting species. Plant–pollinator systems may be susceptible to temporal mismatch if bees and flowering plants differ in their phenological responses to warming temperatures. While the cues that trigger flowering are well‐understood, little is known about what determines bee phenology. Using generalised additive models, we analyzed time‐series data representing 67 bee species collected over 9 years in the Colorado Rocky Mountains to perform the first community‐wide quantification of the drivers of bee phenology. Bee emergence was sensitive to climatic variation, advancing with earlier snowmelt timing, whereas later phenophases were best explained by functional traits including overwintering stage and nest location. Comparison of these findings to a long‐term flower study showed that bee phenology is less sensitive than flower phenology to climatic variation, indicating potential for reduced synchrony of flowers and pollinators under climate change.more » « less
-
null (Ed.)Abstract Rapid climate warming is altering Arctic and alpine tundra ecosystem structure and function, including shifts in plant phenology. While the advancement of green up and flowering are well-documented, it remains unclear whether all phenophases, particularly those later in the season, will shift in unison or respond divergently to warming. Here, we present the largest synthesis to our knowledge of experimental warming effects on tundra plant phenology from the International Tundra Experiment. We examine the effect of warming on a suite of season-wide plant phenophases. Results challenge the expectation that all phenophases will advance in unison to warming. Instead, we find that experimental warming caused: (1) larger phenological shifts in reproductive versus vegetative phenophases and (2) advanced reproductive phenophases and green up but delayed leaf senescence which translated to a lengthening of the growing season by approximately 3%. Patterns were consistent across sites, plant species and over time. The advancement of reproductive seasons and lengthening of growing seasons may have significant consequences for trophic interactions and ecosystem function across the tundra.more » « less
-
As plants continue to respond to global warming with phenological shifts, our understanding of the importance of short‐lived heat events and seasonal weather cues has lagged relative to our understanding of plant responses to broad shifts in mean climate conditions. Here, we explore the importance of warmer‐than‐average days in driving shifts in phenophase duration for spring‐flowering woodland herbs across one growing season. We harnessed the combined power of community science and public gardens, engaging more than 30 volunteers to monitor shifts in phenology (documenting movement from one phenophase to the next) for 198 individual plants of 14 species twice per week for the 2023 growing season (March—October) across five botanic gardens in the midwestern and southeastern US. Gardens included the Holden Arboretum, Kirtland, OH; Dawes Arboretum, Newark, OH; Chicago Botanic Garden, Glencoe, IL; Missouri Botanical Garden, St. Louis, MO; and Huntsville Botanical Garden, Huntsville, AL. We tested: (1) that higher‐than‐average daily temperatures (deviation from 30‐year historical mean daily temperatures for each location) would be related to truncated phenophase durations; and (2) that phenophase durations would vary among species. Our findings support both hypotheses. We documented significant inverse relationships between positive deviations in daily temperature from historic means (e.g., warmer‐than‐average days) and durations of three reproductive phenophases: “First Bud,” “First Ripe Fruit,” and “Early Fruiting.” Similar (non‐significant) trends were noted for several other early‐season phenophases. Additionally, significant differences in mean phenophase durations were detected among the different species, although these differences were inconsistent across plant parts (vegetative, flowering, and fruiting). Results underscore the potential sensitivity of understory herb reproductive phenophases to warmer‐than‐average daily temperatures early in the growing season, contributing to our understanding of phenological responses to short‐term heat events and seasonal weather cues.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fpls.2021.787407
