Adaptive genetic variation to drought in a widely distributed conifer suggests a potential for increasing forest resilience in a drying climate

Abstract

Drought intensity and frequency are increasing under global warming, with soil water availability now being a major factor limiting tree growth in circumboreal forests. Still, the adaptive capacity of trees in the face of future climatic regimes remains poorly documented. Using 1481 annually resolved tree-ring series from 29-yr-old trees, we evaluated the drought sensitivity of 43 white spruce (Picea glauca (Moench) Voss) populations established in a common garden experiment. We show that genetic variation among populations in response to drought plays a significant role in growth resilience. Local genetic adaptation allowed populations from drier geographical origins to grow better, as indicated by higher resilience to extreme drought events, compared with populations from more humid geographical origins. The substantial genetic variation found for growth resilience highlights the possibility of selecting for drought resilience in boreal conifers. As a major research outcome, we showed that adaptive genetic variation in response to changing local conditions can shape drought vulnerability at the intraspecific level. Our findings have wide implications for forest ecosystem management and conservation.

Keywords: common garden experiment; dendroecology; genetics; local adaptation; provenance trial; tree rings; white spruce.

Fig. 1

Conceptual diagram of growth resilience. Definition of drought‐resilience traits: resistance, resilience and recovery of radial tree growth increment in response to a drought episode, as used in the present study and as previously defined by Lloret et al. (2011).

Fig. 2

Climate variation and basal area increments (BAIs) of white spruce provenances. (a) Temporal variation of mean summer (June, July and August) maximum temperatures T _max, total precipitation (Prec) and soil moisture index (SMI) from 1985 to 2007 at the common garden site. Climate deviations from the long‐term mean were estimated as the ratio between the annual mean summer value and the mean summer value for the period 1989–2007. (b) Annual variation in radial tree growth increment (BAI) for the period 1985–2007. Arrows indicate drought years that coincide with abrupt decreases in BAI. (c) Annual variation in radial tree growth increment (BAI) for the period 1999–2005. The different time periods used to calculate the drought‐resilience traits in 2002 are indicated by different colours.

Fig. 3

Climate–growth associations of white spruce provenances. Correlation analyses of basal area increment residual chronologies against the monthly mean soil moisture index (SMI) from May to October of the previous (t − 1) growing season and the current growing season (t) are presented for the period 1989–2007. The scale bar reports positive (red) and negative (blue) correlation coefficients. Significant relationships (P < 0.05) are indicated by dots in the correlation matrix.

Fig. 4

Growth resilience in relation to climate at white spruce provenance origin. Maps of growth resilience (Rl) against (a) the mean annual temperature (MAT) and (b) mean summer soil moisture index (Summer_SMI) for the period 1950–1980. (c) Multivariate adaptive regression spline (MARS) results presenting growth resilience (Rl₂₀₀₂) as a function of both MAT and Summer_SMI. A gridded bivariate spline interpolation was applied to the irregularly spaced observed (left) and predicted (right) resilience data. The extreme provenances along the aridity gradient (i.e. POP_34, POP_37 and POP_7) identified for the observed and predicted Rl₂₀₀₂ values are represented by black circles. The two southern provenances (i.e. POP_25 and POP_43) are represented by black squares. The scale bar indicates low (blue), medium (yellow) and high (red) correlation coefficients. MARS analyses revealed that both Summer_SMI and MAT were significant predictors of growth resilience. Rl₂₀₀₂ was positively correlated to soil moisture in summer (provenances shown in circles), whereas the lowest resilience for POP_43 and POP_25 (provenances shown in black squares) was mainly explained by temperature.