A new phenological metric for use in pheno-climatic models: A case study using herbarium specimens of Streptanthus tortuosus

Long-term trends in global flowering phenology

Flowering phenology is an indicator of the impact of climate change on natural systems. Anthropogenic climate change has progressed over more than two centuries, but ecological studies are mostly short in comparison. Here we harness the large-scale digitization of herbaria specimens to investigate temporal trends in flowering phenology at a global scale. We trained a convolutional neural network model to classify images of angiosperm herbarium specimens as being in flower or not in flower. This model was used to infer flowering across 8 million specimens spanning a century and global scales. We investigated temporal trends in mean flowering date and flowering season duration within ecoregions. We found high diversity of temporal trends in flowering seasonality across ecoregions with a median absolute shift of 2.5 d per decade in flowering date and 1.4 d per decade in flowering season duration. Variability in temporal trends in phenology was higher at low latitudes than at high latitudes. Our study demonstrates the value of digitized herbarium specimens for understanding natural dynamics in a time of change. The higher variability in phenological trends at low latitudes likely reflects the effects of a combination of shifts in temperature and precipitation seasonality, together with lower photoperiodic constraints to flowering.

Phenological Shifts Since 1830 in 29 Native Plant Species of California and Their Responses to Historical Climate Change

Climate change is affecting Mediterranean climate regions, such as California. Retrospective phenological studies are a useful tool to track biological response to these impacts through the use of herbarium-preserved specimens. We used data from more than 12,000 herbarium specimens of 29 dominant native plant species that are characteristic of 12 broadly distributed vegetation types to investigate phenological patterns in response to climate change. We analyzed the trends of four phenophases: preflowering (FBF), flowering (F), fruiting (FS) and growth (DVG), over time (from 1830 to 2023) and through changes in climate variables (from 1896 to 2023). We also examined these trends within California's 10 ecoregions. Among the four phenophases, the strongest response was found in the timing of flowering, which showed an advance in 28 species. Furthermore, 21 species showed sequencing in the advance of two or more phenophases. We highlight the advances found over temperature variables: 10 in FBF, 28 in F, 17 in FS and 18 in DVG. Diverse and less-consistent results were found for water-related variables with 15 species advancing and 11 delaying various phenophases in response to decreasing precipitation and increasing evapotranspiration. Jepson ecoregions displayed a more pronounced advance in F related to time and mean annual temperature in the three of the southern regions compared to the northern ones. This study underscores the role of temperature in driving phenological change, demonstrating how rising temperatures have predominantly advanced phenophase timing. These findings highlight potential threats, including risks of climatic, ecological, and biological imbalances.

Context-dependent concordance between physiological divergence and phenotypic selection in sister taxa with contrasting phenology and mating systems

PREMISE

The study of phenotypic divergence of, and selection on, functional traits in closely related taxa provides the opportunity to detect the role of natural selection in driving diversification. If the strength or direction of selection in field populations differs between taxa in a pattern that is consistent with the phenotypic difference between them, then natural selection reinforces the divergence. Few studies have sought evidence for such concordance for physiological traits.

METHODS

Herbarium specimen records were used to detect phenological differences between sister taxa independent of the effects on flowering time of long-term variation in the climate across collection sites. In the field, physiological divergence in photosynthetic rate, transpiration rate, and instantaneous water-use efficiency were recorded during vegetative growth and flowering in 13 field populations of two taxon pairs of Clarkia, each comprising a self-pollinating and a outcrossing taxon.

RESULTS

Historically, each selfing taxon flowered earlier than its outcrossing sister taxon, independent of the effects of local long-term climatic conditions. Sister taxa differed in all focal traits, but the degree and (in one case) the direction of divergence depended on life stage. In general, self-pollinating taxa had higher gas exchange rates, consistent with their earlier maturation. In 6 of 18 comparisons, patterns of selection were concordant with the phenotypic divergence (or lack thereof) between sister taxa.

CONCLUSIONS

Patterns of selection on physiological traits measured in heterogeneous conditions do not reliably reflect divergence between sister taxa, underscoring the need for replicated studies of the direction of selection within and among taxa.

Machine Learning Undercounts Reproductive Organs on Herbarium Specimens but Accurately Derives Their Quantitative Phenological Status: A Case Study of Streptanthus tortuosus

Machine learning (ML) can accelerate the extraction of phenological data from herbarium specimens; however, no studies have assessed whether ML-derived phenological data can be used reliably to evaluate ecological patterns. In this study, 709 herbarium specimens representing a widespread annual herb, Streptanthus tortuosus, were scored both manually by human observers and by a mask R-CNN object detection model to (1) evaluate the concordance between ML and manually-derived phenological data and (2) determine whether ML-derived data can be used to reliably assess phenological patterns. The ML model generally underestimated the number of reproductive structures present on each specimen; however, when these counts were used to provide a quantitative estimate of the phenological stage of plants on a given sheet (i.e., the phenological index or PI), the ML and manually-derived PI's were highly concordant. Moreover, herbarium specimen age had no effect on the estimated PI of a given sheet. Finally, including ML-derived PIs as predictor variables in phenological models produced estimates of the phenological sensitivity of this species to climate, temporal shifts in flowering time, and the rate of phenological progression that are indistinguishable from those produced by models based on data provided by human observers. This study demonstrates that phenological data extracted using machine learning can be used reliably to estimate the phenological stage of herbarium specimens and to detect phenological patterns.

Region-specific phenological sensitivities and rates of climate warming generate divergent temporal shifts in flowering date across a species' range

PREMISE

Forecasting how species will respond phenologically to future changes in climate is a major challenge. Many studies have focused on estimating species- and community-wide phenological sensitivities to climate to make such predictions, but sensitivities may vary within species, which could result in divergent phenological responses to climate change.

METHODS

We used 743 herbarium specimens of the mountain jewelflower (Streptanthus tortuosus, Brassicaceae) collected over 112 years to investigate whether individuals sampled from relatively warm vs. cool regions differ in their sensitivity to climate and whether this difference has resulted in divergent phenological shifts in response to climate warming.

RESULTS

During the past century, individuals sampled from warm regions exhibited a 20-day advancement in flowering date; individuals in cool regions showed no evidence of a shift. We evaluated two potential drivers of these divergent responses: differences between regions in (1) the degree of phenological sensitivity to climate and (2) the magnitude of climate change experienced by plants, or (3) both. Plants sampled from warm regions were more sensitive to temperature-related variables and were subjected to a greater degree of climate warming than those from cool regions; thus our results suggest that the greater temporal shift in flowering date in warm regions is driven by both of these factors.

CONCLUSIONS

Our results are among the first to demonstrate that species exhibited intraspecific variation in sensitivity to climate and that this variation can contribute to divergent responses to climate change. Future studies attempting to forecast temporal shifts in phenology should consider intraspecific variation.

A New Method for Counting Reproductive Structures in Digitized Herbarium Specimens Using Mask R-CNN

Phenology-the timing of life-history events-is a key trait for understanding responses of organisms to climate. The digitization and online mobilization of herbarium specimens is rapidly advancing our understanding of plant phenological response to climate and climatic change. The current practice of manually harvesting data from individual specimens, however, greatly restricts our ability to scale-up data collection. Recent investigations have demonstrated that machine-learning approaches can facilitate this effort. However, present attempts have focused largely on simplistic binary coding of reproductive phenology (e.g., presence/absence of flowers). Here, we use crowd-sourced phenological data of buds, flowers, and fruits from >3,000 specimens of six common wildflower species of the eastern United States (Anemone canadensis L., A. hepatica L., A. quinquefolia L., Trillium erectum L., T. grandiflorum (Michx.) Salisb., and T. undulatum Wild.) to train models using Mask R-CNN to segment and count phenological features. A single global model was able to automate the binary coding of each of the three reproductive stages with >87% accuracy. We also successfully estimated the relative abundance of each reproductive structure on a specimen with ≥90% accuracy. Precise counting of features was also successful, but accuracy varied with phenological stage and taxon. Specifically, counting flowers was significantly less accurate than buds or fruits likely due to their morphological variability on pressed specimens. Moreover, our Mask R-CNN model provided more reliable data than non-expert crowd-sourcers but not botanical experts, highlighting the importance of high-quality human training data. Finally, we also demonstrated the transferability of our model to automated phenophase detection and counting of the three Trillium species, which have large and conspicuously-shaped reproductive organs. These results highlight the promise of our two-phase crowd-sourcing and machine-learning pipeline to segment and count reproductive features of herbarium specimens, thus providing high-quality data with which to investigate plant responses to ongoing climatic change.

A new fine-grained method for automated visual analysis of herbarium specimens: A case study for phenological data extraction

PREMISE

Herbarium specimens represent an outstanding source of material with which to study plant phenological changes in response to climate change. The fine-scale phenological annotation of such specimens is nevertheless highly time consuming and requires substantial human investment and expertise, which are difficult to rapidly mobilize.

METHODS

We trained and evaluated new deep learning models to automate the detection, segmentation, and classification of four reproductive structures of Streptanthus tortuosus (flower buds, flowers, immature fruits, and mature fruits). We used a training data set of 21 digitized herbarium sheets for which the position and outlines of 1036 reproductive structures were annotated manually. We adjusted the hyperparameters of a mask R-CNN (regional convolutional neural network) to this specific task and evaluated the resulting trained models for their ability to count reproductive structures and estimate their size.

RESULTS

The main outcome of our study is that the performance of detection and segmentation can vary significantly with: (i) the type of annotations used for training, (ii) the type of reproductive structures, and (iii) the size of the reproductive structures. In the case of Streptanthus tortuosus, the method can provide quite accurate estimates (77.9% of cases) of the number of reproductive structures, which is better estimated for flowers than for immature fruits and buds. The size estimation results are also encouraging, showing a difference of only a few millimeters between the predicted and actual sizes of buds and flowers.

DISCUSSION

This method has great potential for automating the analysis of reproductive structures in high-resolution images of herbarium sheets. Deeper investigations regarding the taxonomic scalability of this approach and its potential improvement will be conducted in future work.

Machine Learning Using Digitized Herbarium Specimens to Advance Phenological Research

Machine learning (ML) has great potential to drive scientific discovery by harvesting data from images of herbarium specimens—preserved plant material curated in natural history collections—but ML techniques have only recently been applied to this rich resource. ML has particularly strong prospects for the study of plant phenological events such as growth and reproduction. As a major indicator of climate change, driver of ecological processes, and critical determinant of plant fitness, plant phenology is an important frontier for the application of ML techniques for science and society. In the present article, we describe a generalized, modular ML workflow for extracting phenological data from images of herbarium specimens, and we discuss the advantages, limitations, and potential future improvements of this workflow. Strategic research and investment in specimen-based ML methods, along with the aggregation of herbarium specimen data, may give rise to a better understanding of life on Earth.