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.

Premise: Herbarium specimens have been used to detect climate‐induced shifts in flowering time by using the day of year of collection (DOY) as a proxy for first or peak flowering date. Variation among herbarium sheets in their phenological status, however, undermines the assumption that DOY accurately represents any particular phenophase. Ignoring this variation can reduce the explanatory power of pheno‐climatic models (PCMs) designed to predict the effects of climate on flowering date.Methods: Here we present a protocol for the phenological scoring of imaged herbarium specimens using an ImageJ plugin, and we introduce a quantitative metric of a specimen's phenological status, the phenological index (PI), which we use in PCMs to control for phenological variation among specimens of Streptanthus tortuosus (Brassicaceeae) when testing for the effects of climate on DOY. We demonstrate that including PI as an independent variable improves model fit.Results: Including PI in PCMs increased the model R² relative to PCMs that excluded PI; regression coefficients for climatic parameters, however, remained constant.Discussion: Our protocol provides a simple, quantitative phenological metric for any observed plant. Including PI in PCMs increases R² and enables predictions of the DOY of any phenophase under any specified climatic conditions.

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.

Offspring size is a key functional trait that can affect subsequent life history stages; in many species, it exhibits both local adaptation and phenotypic plasticity. Variation among populations in offspring size may be explained by various factors, including local climatic conditions. However, geographic variation in climate may be partitioned into long‐term and interannual sources of variation, which may differ in their effects on population mean offspring size. To assess environmental correlates of offspring size, we evaluated geographic variation in seed mass among 88 populations representing 6 species ofStreptanthus(Brassicaceae) distributed across a broad climatic gradient in California. We examined the effects of temperature‐mediated growing season length and precipitation on population mean seed mass to determine whether it is best explained by (1) long‐term mean climatic conditions; (2) interannual climate anomalies (i.e., deviations in climate from long‐term means) during the year of seed development, or (3) interactions between climate variables. Both long‐term mean climate and climate anomalies in the year of collection were associated with population mean seed mass, but their effects differed in direction and magnitude. Relatively large seeds were produced at chronically wet sites but also during drier‐than‐average years. This contrast indicates that these associations may be generated by different mechanisms (i.e., adaptive evolution vs. phenotypic plasticity) and may be evidence of countergradient plasticity in seed mass. In addition, populations occurring in locations characterized by relatively long growing seasons produced comparatively large seeds, particularly among chronically dry sites. This study highlights the need to consider that the responses of seed mass to long‐term versus recent climatic conditions may differ and that climate variables may interact to predict seed mass. Such considerations are especially important when using these patterns to forecast the long‐ and short‐term responses of seed mass to climate change. The results presented here also contribute to our broader understanding of how climate drives long‐term (e.g., local adaptation) and short‐term (e.g., phenotypic plasticity) variation in functional traits, such as offspring size across landscapes.

Eucalyptus globulus is native to southeastern Australia, including the island of Tasmania, but is one of the most widely grown hardwood forestry species in the world and is naturalized on several continents. We studied its naturalization in California, where the species has been planted for over 150 years. We sampled 70 E. globulus trees from 53 locations spanning the entire range of the species in California to quantify the genetic variation present and test whether particular genotypes or native origin affect variation in naturalization among locations. Diversity and native affinities were determined based on six nuclear microsatellite markers and sequences from a highly variable chloroplast DNA region (J_LA+). The likely native origin was determined by DNA-based comparison with a range-wide native stand collection. Most of California’s E. globulus originated from eastern Tasmania. Genetic diversity in California is greatly reduced compared with that of the native Australian population, with a single chloroplast haplotype occurring in 66% of the Californian samples. Throughout California, the degree of E. globulus naturalization varies widely but was not associated with genotype or native origin of the trees, arguing that factors such as local climate and disturbance are more important than pre-introduction evolutionary history.