We performed over 19,000 lure-assisted, underwater visual fish census transects at over 140 shallow coastal sampling locations in the mid- eastern Adriatic sea of the Croatian mainland and islands, recording all fish taxa observed, their predatory behavior in response to the lure, and the cover of benthic habitats with which they were associated. We hypothesized that prey habitat preference was a learned or selected response to aggressive behavior by piscivorous mesopredators, and predicted that mobile prey would be spatially segregated from aggressive predators into different benthic habitats within local sampling sites. We found that aggressive piscivores were primarily wait-chase or cruise-chase mesopredators that preferentially foraged along heterogeneous habitat edges within juxtapositions of rock, unconsolidated sediment, macroalgae (Cystoseira spp.) and seagrass (usually Posidonia oceanica). Prey species and less aggressive piscivores avoided these heterogeneous habitats and preferred more homogeneous habitats that the aggressive predators in turn avoided. We found strong and consistent spatial segregation between aggressive predators on the one hand, and less aggressive predators and prey on the other hand. These results are consistent with the hypothesis that aggressive behavior by piscivorous species is the primary organizing force shaping assembly of fish communities at our study sites, driving preference and occupancy of heterogeneous and homogeneous benthic habitats. Management of shallow benthic resources should recognize the value of complementarity in habitats allowing coexistence of predators and prey through contrasting habitat preferences.

Understanding the causes of variation in faunal abundance and diversity across shallow coastal habitats is a fundamental goal of marine ecology. Field methods for inferring a habitat effect on population density and predation risk are informative only if method biases are equal across habitats and species. We hypothesised that observation of fixed lures has a species by bias interaction if sampled species have different modes of predation, and that these biases are overcome by use of moving lures. We tested this hypothesis by observation of fixed and moving lures within seagrass and bare sediment in the Novigrad Sea, Croatian Adriatic. Both methods showed that ambush predators peaked in seagrass, wait–chasers peaked over bare sediment, and move–chasers were abundant in both. Stationary lures underestimated wait–chase and wait–ambush predators relative to moving lures, whereas moving lures did not underestimate the density of predators. These results indicate that stationary lures can underestimate both fish abundance and predation risk in the presence of waiting predators, and that if waiting predators are more abundant in structured habitat, then stationary lures will underestimate the predation risk within such habitats. Use of moving lures may be preferable for comparing habitats differing in structural complexity and frequency of predation modes.