Search

While much attention has been paid to the climatic controls of species' range limits, other factors such as dispersal limitation are also important. Temperature is an important control of the distribution of coastal mangrove forests, and mangrove expansion at multiple poleward range limits has been linked to increasing temperatures. However, mangrove abundances at other poleward range limits have been surprisingly insensitive to climate change, indicating other drivers of range limitation. For example, along the west coast of North America, the poleward mangrove range limits are found on the Baja California and mainland coasts of Mexico, between 26°48ʹ and 30°18ʹN. Non‐climatic factors may play an important role in setting these range limits as 1) the abundance of range limit populations has been relatively insensitive to climate variability and 2) an introduced population of mangroves has persisted hundreds of kilometers north of the natural range limits. We combined a species distribution model with a high‐resolution oceanographic transport model to identify the roles of climate and dispersal limitation in controlling mangrove distributions. We identified estuarine habitat that is likely climatically suitable for mangroves north of the current range limits. However, propagules from current mangrove populations are unlikely to reach these suitable locations due to prevailing ocean currents and geomorphic factors that create a patchy distribution of estuarine habitat with large between‐patch distances. Thus, although climate change is driving range shifts of mangroves in multiple regions around the world, dispersal is currently limiting poleward mangrove expansion at several range limits, including the west coast of North America. [ABSTRACT FROM AUTHOR]

Species distribution models (SDMs) are widely used in ecology, biogeography and conservation biology to estimate relationships between environmental variables and species occurrence data and make predictions of how their distributions vary in space and time. During the past two decades, the field has increasingly made use of machine learning approaches for constructing and validating SDMs. Model accuracy has steadily increased as a result, but the interpretability of the fitted models, for example the relative importance of predictor variables or their causal effects on focal species, has not always kept pace. Here we draw attention to an emerging subdiscipline of artificial intelligence, explainable AI (xAI), as a toolbox for better interpreting SDMs. xAI aims at deciphering the behavior of complex statistical or machine learning models (e.g. neural networks, random forests, boosted regression trees), and can produce more transparent and understandable SDM predictions. We describe the rationale behind xAI and provide a list of tools that can be used to help ecological modelers better understand complex model behavior at different scales. As an example, we perform a reproducible SDM analysis in R on the African elephant and showcase some xAI tools such as local interpretable model‐agnostic explanation (LIME) to help interpret local‐scale behavior of the model. We conclude with what we see as the benefits and caveats of these techniques and advocate for their use to improve the interpretability of machine learning SDMs. [ABSTRACT FROM AUTHOR]