We describe the development of a comprehensive set of marine mammal habitat models for the US east coast and Gulf of Mexico and their delivery through an online mapping portal. Drawing from datasets in the online OBIS-SEAMAP geo-database, we integrated surveys conducted by ship (n = 36) and aircraft (n = 16), weighting a generalized additive model (GAM) by minutes surveyed within space−time grid cells to harmonize effort between the 2 survey platforms. For each of 16 cetacean species guilds, we

more »

... predicted the probability of occurrence from static environmental variables (water depth, distance to shore, distance to continental shelf break) and time-varying conditions (monthly sea surface temperature). To generate maps of presence versus absence, receiver operator characteristic (ROC) curves were used to define the optimal threshold that minimizes false positive and false negative error rates. We integrated model outputs, including tables (species in guilds, input surveys) and plots (fit of environmental variables, ROC curve), into an online spatial decision support system (SDSS), allowing for easy navigation of models by taxon, region, season, and data provider. Users can define regions of interest and extract statistical summaries of the model for that region. The SDSS also displays density models from other providers and regions (e.g. Pacific Ocean). This versatile, easy-to-use online system enables the application of these habitat models to real-world conservation and management issues. Finally, we discuss the ecological relevance of these model outputs and identify key data gaps across species, regions, and seasons. KEY WORDS: Species distribution model · Habitat · Cetacea · Generalized additive model · Spatial decision support system · Atlantic Ocean · Gulf of Mexico Resale or republication not permitted without written consent of the publisher Contribution to the Theme Section 'Beyond marine mammal habitat modeling'