"Closer-to-home" strategy benefits juvenile survival in a long-distance migratory bird

Abstract

Human-induced changes in the climate and environment that occur at an unprecedented speed are challenging the existence of migratory species. Faced with these new challenges, species with diverse and flexible migratory behaviors may suffer less from population decline, as they may be better at responding to these changes by altering their migratory behavior. At the individual level, variations in migratory behavior may lead to differences in fitness and subsequently influence the population's demographic dynamics. Using lifetime GPS bio-logging data from 169 white storks (Ciconia ciconia), we explore whether the recently shortened migration distance of storks affects their survival during different stages of their juvenile life. We also explore how other variations in migratory decisions (i.e., time, destination), movement activity (measured using overall body dynamic acceleration), and early life conditions influence juvenile survival. We observed that their first autumn migration was the riskiest period for juvenile white storks. Individuals that migrated shorter distances and fledged earlier experienced lower mortality risks. In addition, higher movement activity and overwintering "closer-to-home" (with 84.21% of the tracked individuals stayed Europe or North Africa) were associated with higher survival. Our study shows how avian migrants can change life history decisions over only a few decades, and thus it helps us to understand and predict how migrants respond to the rapidly changing world.

Keywords: ODBA; bio‐logging; long‐distant migration; migration strategy; survival.

Figure 1

Movement trajectories of storks during the study period (i.e., postfledging time, first autumn migration, and wintering period). Filled circles indicate the death locations. Trajectories ending with open circles indicate censored individuals (alive or vanished). Trajectories are color‐coded based on the total number of survival days. The bottom right insert shows the survival curve with 95% confidence interval (shaded area). Short vertical lines indicate censored events. Dashed lines correspond to median survival time. (Background map from Natural Earth)

Figure 2

Estimated log‐relative hazard of each covariate of the Cox model for the first autumn migration (a–d) and first winter (e, f), with histogram of data distribution at the bottom: (a) median daily migration overall dynamic body acceleration (ODBA), (b) fledging date, (c) median daily migration distance, (d) interaction between fledging date and migration distance, (e) median daily wintering ODBA, and (f) wintering region, that is, Europe (EU), North Africa (NA), and Sub‐Saharan Africa (SA). Black line or points represent the predicted values adjusted by the mean or the reference level of other model covariates. Gray bands or bars correspond to the 95% confidence limit. Dashed vertical or horizontal lines show the median value of covariates. DOY‐day of the year