Do different camera trap lures result in different detection rates of vertebrates because of their attractiveness to invertebrates?

Summary The type of attractant used in camera trap lures is recognised as an important methodological decision. We investigated whether the type of attractant in lures indirectly influences detectability of wildlife on cameras via differential attraction of invertebrates which themselves constitute prey of insectivorous animals. We indexed invertebrate abundance using pitfall and sticky‐traps at 36 camera stations deployed in a Latin Squares design for 5 days, with three lure options (peanut‐butter, tuna oil and control) in a coastal mosaic, at Cape Otway, Victoria, Australia. We classified vegetation types (habitat) as: low (no or sparse), medium (grass), and high (shrubs) from aerial imagery and estimated their percentage cover at each grid point (medium and high were uncorrelated and included as separate variables in models). We first examine if attractant types or the habitat influence invertebrate abundance and assemblage, and then examine whether invertebrate abundance influences vertebrate detectability on cameras. There was a trend for the composition of terrestrial invertebrate assemblages to be influenced by lure type (peanut‐butter, tuna oil and control attractants) and the proportional cover of medium height vegetation within 20 m; however, assemblage composition was clearly influenced by the proportional area of high vegetation cover within 20 m. The detection probability of insectivorous birds increased where medium‐sized (2.5–5 mm) flying invertebrates were present whereas insectivorous mammal detectability increased with terrestrial invertebrate species richness. Mammal detections are more likely associated with use of habitats that have more diverse invertebrate communities. This study provides some support to the hypothesis of the indirect mechanism whereby bird detections are influenced by invertebrate attraction to lures. Therefore, lure choice for camera traps is critical and the possibility of guild‐level biases in detection suggests that cautious interpretation of results is required.