Body condition and habitat use by Hermann's tortoises in burnt and intact habitats

Abstract

In Mediterranean regions, fires threaten terrestrial tortoises. Nevertheless, varying proportions of adults survive fire; these surviving individuals can play a central role for population recovery. The regions devastated by fire often include important habitat of Hermann's tortoises (Testudo hermanni hermanni), so assessing the ability of survivors to persist is essential for conserving the species. Body-condition indices provide an integrative estimate of how well individuals cope with environmental variations and impacts, including fires. Between 2002 and 2009, we monitored Hermann's tortoises in intact and burnt habitats in southeastern France. In summer 2003, a strong fire ravaged half of the surveyed zone, providing an opportunity to compare body condition of tortoises between intact and burnt areas over time. Six years later, the impact of fire on vegetation was still marked; large trees were abundant in the intact area, whereas open shrub vegetation prevailed in the burnt area. In both areas, the mean body condition of tortoises fluctuated over time; however, there were no differences between the two areas. A radio-tracking experiment demonstrated that individuals from each area were residents, and not vagrants commuting between areas. We also assessed changes in body condition and microhabitat use in radio-tracked individuals. We found no significant differences between the tortoises living in the burnt and intact areas, despite subtle differences in habitat use.

In conclusion: (i) surviving tortoises in an area ravaged by fire can maintain their body condition like individuals living in an intact area, and thus, individuals from burnt areas should not be translocated to supposedly better areas; and (ii) depopulated burnt areas are likely to be appropriate for population-augmentation programmes.

Keywords: Fire mortality; Mediterranean region; Testudo hermanni; habitat; reptiles.

Figure 1:

Mean and 1 SE (error bars) percentage cover of the main vegetation types (large trees with a crown wider than 8 m, smaller trees and shrubs) and open ground (herbaceous material, no vegetation) for intact (grey bars) and burnt habitats (black bars) in 2009, 6 years after the 2003 fire. Note that statistics were not performed on percentages, but on values ranging between zero and one (see main text).

Figure 2:

Mean ±1 SD temperatures recorded every 30 min, using physical models, in open microhabitat (herbaceous layer, n = 4) and in closed microhabitat (ground beneath large trees, thick shrubs, n = 4). Data presented were recorded between April and May 2009, when tortoises are active. The grey shaded area indicates the range of preferred body temperatures during activity in tortoises belonging to the Testudo genus; temperatures above 40°C (grey dashed line) can be lethal (Lagarde et al., 2012).

Figure 3:

Comparison of mean annual body condition (mass scaled by size; residuals, see main text) of tortoises monitored in two areas, intact and burnt. A major fire occurred in summer 2003 (note that most tortoises, 80%, were assessed before the fire in 2003). Means are expressed ±1 SE; numbers indicate sample size. Due to small sample sizes (n < 10 tortoises observed per year), means could not be calculated reliably in 2006 and 2008.

Figure 4:

Changes in mean body condition (±1 SE) in control and displaced radio-tracked tortoises in intact and burnt areas, from 10 April to 20 May 2009. Sample size was six for each group.

Figure 5:

Mean (±1 SE) daily distance travelled by control (n = 12; open bars) and displaced radio-tracked tortoises (n = 12; hatched bars). Intact and burnt areas are indicated in white and grey, respectively (sample size was six for each group).

Figure 6:

Mean (±1 SE, n = 6 per group) microhabitat use (expressed as a percentage) by control (black bars) and displaced (dark grey bars) radio-tracked tortoises in intact (A; top graph) and burnt areas (B; bottom graph). Significant selection was evaluated as high (preference) or low (aversion) compared with randomly sampled microhabitats (Random; light grey bars). *Statistically significant differences (Wilcoxon test P < 0.05; see main text).