Landscape Analysis of Adult Florida Panther Habitat

Abstract

Historically occurring throughout the southeastern United States, the Florida panther is now restricted to less than 5% of its historic range in one breeding population located in southern Florida. Using radio-telemetry data from 87 prime-aged (≥3 years old) adult panthers (35 males and 52 females) during the period 2004 through 2013 (28,720 radio-locations), we analyzed the characteristics of the occupied area and used those attributes in a random forest model to develop a predictive distribution map for resident breeding panthers in southern Florida. Using 10-fold cross validation, the model was 87.5 % accurate in predicting presence or absence of panthers in the 16,678 km2 study area. Analysis of variable importance indicated that the amount of forests and forest edge, hydrology, and human population density were the most important factors determining presence or absence of panthers. Sensitivity analysis showed that the presence of human populations, roads, and agriculture (other than pasture) had strong negative effects on the probability of panther presence. Forest cover and forest edge had strong positive effects. The median model-predicted probability of presence for panther home ranges was 0.81 (0.82 for females and 0.74 for males). The model identified 5579 km2 of suitable breeding habitat remaining in southern Florida; 1399 km2 (25%) of this habitat is in non-protected private ownership. Because there is less panther habitat remaining than previously thought, we recommend that all remaining breeding habitat in south Florida should be maintained, and the current panther range should be expanded into south-central Florida. This model should be useful for evaluating the impacts of future development projects, in prioritizing areas for panther conservation, and in evaluating the potential impacts of sea-level rise and changes in hydrology.

Fig 1. Location of the Florida panther study area and major land cover classes.

(a) Main map shows the study area in relation to the Primary Zone, an area of focus by conservation agencies. Inset shows the location of resident adult telemetry points from 2004 through 2013. Breeding panthers do not occur north of the Caloosahatchee River. (b) Geographical distribution of 10 major land cover categories within the study area, used as explanatory variables in the random forest model. Categories were distilled from the Florida Land Use and Cover Classification System (FLUCCS).

Fig 2. Landscape characteristics within the study area used as explanatory variables.

(a) amount of forest edge (km/km²); (b) average water depths during the dry season (m); (c) area-weighted average human population density (people/km²); (d) road density (km/km²).

Fig 3. Probability of presence and adult panther habitat.

(a) Probability of presence (P) of resident adult panthers throughout the study area in south Florida, as predicted by the random forest model. (b) Grid cells with P > 0.338 are considered to be adult (breeding) panther habitat. Adult panther habitat is shown in relation to the Primary and Secondary Zones.

Fig 4. Variable importance.

Importance was calculated based on mean decrease in model accuracy (black bars) and mean decrease in Gini index (gray bars). Importance scores were standardized relative to the most important variable by each method. Variables are ranked from highest to lowest importance, based on combined scores from the two methods. Wet_For = wetland forest, Pop_Dens = human population density, For_Edge = forest edge, dry_depth = average dry season water depth, wet_depth = average wet season water depth, Wet_Shrub = wetland shrub, Rd_Dens = road density, FW_Wet = open freshwater wetlands, Ag = agricultural, Up_For = upland forest, Grass = grasslands/dry prairies, Water = open water, Up_Shrub = upland shrub, SW_Wet = saltwater wetland.

Fig 5. Sensitivity of model predictions (probability of presence, P) to changes in selected explanatory variables.

(a) human population density; (b) road density; (c) forest edge; (d) wetland forest cover; (e) agriculture (other than pasture); (f) average dry season water depth. The response to each variable was examined at high, medium and low ranges of P. The P range where the variable had its largest effect is shown.

Fig 6. Average probability of presence in Florida panther home ranges.

Males (open circles): median = 0.74, n = 35; females (solid circles): median = 0.82, n = 52. One male home range (average P = 0.35) is not shown.