Grassland allergenicity increases with urbanisation and plant invasions

Abstract

Pollen allergies have been on the rise in cities, where anthropogenic disturbances, warmer climate and introduced species are shaping novel urban ecosystems. Yet, the allergenic potential of these urban ecosystems, in particular spontaneous vegetation outside parks and gardens, remains poorly known. We quantified the allergenic properties of 56 dry grasslands along a double gradient of urbanisation and plant invasion in Berlin (Germany). 30% of grassland species were classified as allergenic, most of them being natives. Urbanisation was associated with an increase in abundance and diversity of pollen allergens, mainly driven by an increase in allergenic non-native plants. While not inherently more allergenic than native plants, the pool of non-natives contributed a larger biochemical diversity of allergens and flowered later than natives, creating a broader potential spectrum of allergy. Managing novel risks to urban public health will involve not only targeted action on allergenic non-natives, but also policies at the habitat scale favouring plant community assembly of a diverse, low-allergenicity vegetation. Similar approaches could be easily replicated in other cities to provide a broad quantification and mapping of urban allergy risks and drivers.

Keywords: Alien plants; Biochemical diversity; Ecosystem disservices; Novel ecosystems; Public health; Urban ecology.

Fig. 1

a Map of 56 dry grassland plots in the city of Berlin, Germany. Each square corresponds to a 4 × 4 m grassland plot. The color gradient represents the percentage of impervious surfaces (data from the Berlin senate). Note that five plots were located outside the borders of Berlin, in rural areas of the Brandenburg region. Example grassland plots: b rural grassland in a wide clearing of the Wannsee forest; c sub-urban grassland patch in the Schöneberg district; d urban grassland next to Nordbahnhof train station. Credit: Technische Universität Berlin 2016

Fig. 2

Allergenic species cover and richness in 56 Berlin grasslands along gradients of urbanisation and biotic novelty. Cumulative cover of all allergenic species (a, b), as well as the cover (c, d) and richness (e, f) of non-native allergenics are represented as a function of urbanisation (% impervious surfaces in a 500 m radius) and the proportion of neophytes in each grassland community. Gaussian and Poisson regressions were fitted for cover and richness, respectively. Regression lines with standard errors are represented when significant (solid line; P < 0.05). Statistics for the models are given above panels (Likelihood-ratio test: *P < 0.05; **P < 0.01; ***P < 0.001; ns, P ≥ 0.05)

Fig. 3

Potential allergenic value (PAV) of grassland communities along the urbanisation gradient (% Impervious surfaces). a Mean_PAV increased with urbanisation when the proportion of neophytes was high. This positive interaction is illustrated with partial regression lines for three values of proportion of neophytes (− SD = 0.016, Mean = 0.065, + SD = 0.113). Statistics for the linear model with interaction are indicated. b Mean PAV of archaeophytes present in each community also increased with urbanisation. Statistics for the linear model are indicated (details in Table S3). Statistical significance is indicated with stars: *P < 0.05; **P < 0.01

Fig. 4

Flowering phenology of 216 urban grassland species divided by introduction status. Panels represent the distribution of a the first month of flowering, b the last month of flowering and c flowering length (in months). Differences between groups (natives, archaeophytes, neophytes) were tested with a bootstrapped non-parametric ANOVA. Post-hoc differences between groups are represented by letters based on bootstrap confidence intervals. Significance levels as indicated previously

Fig. 5

Seasonal distribution of flowering allergenic species and allergen families in Berlin grasslands. The 56 plots of grasslands were clustered in three balanced groups (n number of grassland plots per cluster) according to the % of impervious surfaces in a 500 m buffer: < 7% for near rural; between 7 and 30% for low urban; > 30% for high urban. a–c Potential number of allergenic species flowering each month in grassland communities. For each month, the expected number of unique flowering allergenic species present across a grassland cluster was calculated based on species flowering phenology. Species were divided by introduction status: natives (green), archaeophytes (blue) and neophytes (purple). d–f Number of unique protein allergen families potentially produced per month, calculated for each floristic status and grassland cluster. Because some protein families were redundant between floristic status groups, the total number of unique allergen families (grey line) is not equal to the sum of the three groups