Constructing ecological indices for urban environments using species distribution models

Abstract In an increasingly urbanized world, there is a need to study urban areas as their own class of ecosystems well assess the impacts anthropogenic on biodiversity. However, collecting sufficient number species observations estimate patterns biodiversity in city can be costly. Here we investigated use community science-based data occurrences, combined with distribution models (SDMs), built using MaxEnt and remotely-sensed measures environment, predict across environment Los Angeles. By selecting most accurate SDMs, then summarizing these by class, were able produce two richness (SRMs) for Aves Magnoliopsida how they respond variety natural environmental gradients. We found that considered native Angeles tend have significantly more SDMs than non-native counterparts. For all this variables describing activities, such housing density alterations land cover, influential factors, terrain proximity freshwater, shaping SDMs. Using random forest model our SRMs could account approximately 54% 62% predicted variation classes respectively. used roles factors them.