Stochastic atmospheric assistance and the use of emergency staging sites by migrants

Abstract

Numerous animals move vast distances through media with stochastic dynamic properties. Avian migrants must cope with variable wind speeds and directions en route, which potentially jeopardize fine-tuned migration routes and itineraries. We show how unpredictable winds affect flight times and the use of an intermediate staging site by red knots (Calidris canutus canutus) migrating from west Africa to the central north Siberian breeding areas via the German Wadden Sea. A dynamic migration model incorporating wind conditions during flight shows that flight durations between Mauritania and the Wadden Sea vary between 2 and 8 days. The number of birds counted at the only known intermediate staging site on the French Atlantic coast was strongly positively correlated with simulated flight times. In addition, particularly light-weight birds occurred at this location. These independent results support the idea that stochastic wind conditions are the main driver of the use of this intermediate stopover site as an emergency staging area. Because of the ubiquity of stochastically varying media, we expect such emergency habitats to exist in many other migratory systems, both airborne and oceanic. Our model provides a tool to quantify the effect of winds and currents en route.

Figure 1.

Simulated spring knot migration along the great circle route (a straight line in the chosen map projection) from Banc d'Arguin, Mauritania (circled 1), through their potential staging site along the French Atlantic Coast at (circled 2) to their main stopover in the German Wadden Sea (circled 3). (a) Flight trajectories for 1985 (left) and 1986 (right), with 5 May as the starting date. Each segment marks a 6 h time interval. (b) The probability density functions of cumulative flight at latitudes (i) up to 54° N, (ii) up to 45° N, (iii) up to 36° N and (iv) up to 27° N, over all years (1979–2007) and all starting dates (1–10 May) per pressure level.

Figure 2.

Flight times per simulation and mean flight times in relation to observations. (a) The checkerboard plots show simulated number of flight days per pressure level. Each grid cell represents a separate simulation. The graphs in the margins highlight the mean and range of flight time by grouping the simulations per year (above) and per start date (left). The circles in the graphs above the plots represent observations in France. (b) Observations (circles) and their corresponding years and linear regression (black line) for number of bird-days and the respective mean flight time per pressure level (n = 8). Grey lines represent 95 per cent confidence boundaries.