Oil palm monoculture induces drastic erosion of an Amazonian forest mammal fauna

Abstract

Oil palm monoculture comprises one of the most financially attractive land-use options in tropical forests, but cropland suitability overlaps the distribution of many highly threatened vertebrate species. We investigated how forest mammals respond to a landscape mosaic, including mature oil palm plantations and primary forest patches in Eastern Amazonia. Using both line-transect censuses (LTC) and camera-trapping (CT), we quantified the general patterns of mammal community structure and attempted to identify both species life-history traits and the environmental and spatial covariates that govern species intolerance to oil palm monoculture. Considering mammal species richness, abundance, and species composition, oil palm plantations were consistently depauperate compared to the adjacent primary forest, but responses differed between functional groups. The degree of forest habitat dependency was a leading trait, determining compositional dissimilarities across habitats. Considering both the LTC and CT data, distance from the forest-plantation interface had a significant effect on mammal assemblages within each habitat type. Approximately 87% of all species detected within oil palm were never farther than 1300 m from the forest edge. Our study clearly reinforces the notion that conventional oil palm plantations are extremely hostile to native tropical forest biodiversity, which does not bode well given prospects for oil palm expansion in both aging and new Amazonian deforestation frontiers.

Fig 1. Location of the study area.

Location of the study area in Eastern Brazilian Amazonia (solid square in inset map of South America). The main map represents the boundaries of the study area and the spatial distribution of 16 transects (white lines) in both habitat types, along which line-transect censuses and camera-trapping surveys were conducted. Dark green and orange polygons indicate primary forest and oil palm plantations, respectively, within the landscape mosaic. The diagram (lower right) provides details of the spatial configuration of camera-trapping stations along one of the transects. Inset figures show the typical structure and vertical profile of each habitat type: oil palm plantations (above) and primary forest (below). The background shows remaining forest cover, represented by different shades of green, and anthropogenic land cover (e.g., pasture and agriculture, shown in light brown) across the entire neighboring region. The map and satellite free source: MapBiomas Project [2017] Brazil's Annual Coverage and Land Use Map Series, acessed in [2017] link: [http://mapbiomas.org].

Fig 2. Comparison between oil palm plantations and forest considering overall patterns of mammal assemblage.

Box and violin plots comparing the general patterns of mammal community structure between primary forest (in green) and oil palm plantations (in yellow), based on either line transect censuses (left panels) or camera trapping surveys (right panels). Four mammal assemblage properties were quantified: (A) Rarefied species richness; (B) Aggregate abundance; (C) Aggregate biomass; and (D) Community evenness.

Fig 3. Relative abundance rates of terrestrial and arboreal mammal species observed in oil palm plantations and primary forest.

Relative abundance rates in oil palm plantations (left panels: A, C) and primary forest (right panels: B, D) on the basis of camera trapping (upper panels: A, B) and line transect censuses (lower panels: C, D). Mammal species are represented by the first four letters of each genus and first four letters of each species, and ordered top to bottom in decreasing levels of abundance in primary forest.

Fig 4. Relative abundance of terrestrial and arboreal mammal species along a distance gradient intersecting both oil palm plantations and primary forest.

Distance gradient of oil palm plantations (yellow circles) and primary forest (green circles). Survey distances covered a gradient of up to 3500 m in oil palm and over 12,000 m in primary forest. Vertical red dashed line represents a 0-m distance along the edge interface between these two habitat types. Species are ordered according to their higher mammalian taxa (orders). Panels on the left (A) and right (B) represent data based on camera trapping and line transect censuses, respectively. Circle sizes are scaled according to log-transformed (ln x + 1) measures of local abundance based on either sampling technique. Very small dots represent non-detections at any given sampling point.

Fig 5. Principal Coordinates Analysis (PCoA) ordination of the mammal assemblage structure in primary forest and oil palm plantations across the study landscape.

Mammal assemblage structure in primary forest (PF, green circles) and oil palm plantations (OP, yellow circles). PCoA plots are based on the dissimilarity matrix derived from the relative abundance data for each species based on either (A) line transect censuses or (B) camera trapping.

Fig 6. Coefficient estimates (± 95% confidence intervals) showing the magnitude and direction of effects of different explanatory variables.

Effects of different explanatory variables considering either the line transect census data (A, C) or camera trapping data (B, D). Top panels (A, B) show effect sizes for species richness; bottom panels (C, D) show effect sizes for overall abundance. Explanatory variables included Edge_(d): distance to the nearest edge between primary forest and adjacent oil palm plantation; Basal area of native vegetation; Stream_(d): distance to the nearest perennial stream; and Patch area: size of any given habitat patch (in ha).