Accurate forecasts of species distributions in response to a changing climate are essential for proactive management and conservation decision-making. However, species distribution models (SDMs) often have limited capacity to produce robust forecasts under novel environmental conditions, partly due to limitations in model training data. Model-based approaches that leverage diverse types of data have advanced over the last decade, yet their forecasting skill, especially during episodic climatic events, remains uncertain. Here, we develop a suite of SDMs for a commercially important fishery species, albacore tuna (Thunnus alalunga), to evaluate forecast skill under marine heatwave conditions. We compare models that use different methods to leverage data sources (data pooling vs. joint likelihood) and to address spatial dependence (environmental and spatial effects vs. environmental-only) to assess their relative performance in predicting species distributions under novel environmental conditions. Our results indicate model performance declined across all model types as environmental novelty increased, as expected. However, joint-likelihood approaches were more resilient to novel conditions, demonstrating greater predictive skill and ecological realism than traditional SDMs. These results suggest that ecological forecasts under novel environmental conditions are more skillful with a model framework that accounts for unmeasured spatial and temporal variability and uses model-based data integration to explicitly leverage diverse data types. As access to diverse data sources continues to increase, maximizing their utility will be key for delivering accurate forecasts of species distributions and advancing proactive, climate-ready management and conservation strategies.

Species distribution models (SDMs) are becoming an important tool for marine conservation and management. Yet while there is an increasing diversity and volume of marine biodiversity data for training SDMs, little practical guidance is available on how to leverage distinct data types to build robust models. We explored the effect of different data types on the fit, performance and predictive ability of SDMs by comparing models trained with four data types for a heavily exploited pelagic fish, the blue shark (Prionace glauca), in the Northwest Atlantic: two fishery-dependent (conventional mark-recapture tags, fisheries observer records) and two fishery-independent (satellite-linked electronic tags, pop-up archival tags). We found that all four data types can result in robust models, but differences among spatial predictions highlighted the need to consider ecological realism in model selection and interpretation regardless of data type. Differences among models were primarily attributed to biases in how each data type, and the associated representation of absences, sampled the environment and summarized the resulting species distributions. Outputs from model ensembles and a model trained on all pooled data both proved effective for combining inferences across data types and provided more ecologically realistic predictions than individual models. Our results provide valuable guidance for practitioners developing SDMs. With increasing access to diverse data sources, future work should further develop truly integrative modeling approaches that can explicitly leverage strengths of individual data types while statistically accounting for limitations, such as sampling biases.