Modelling species distribution at the boundaries of the Earth's climate

Correlative species distribution models (SDMs) are widely used to project species’ responses to global changes. The climatic niche of a species is calibrated under current climate conditions and then projected in space and/or time, making model extrapolation an important concern. This issue is particularly relevant when considering species that live simultaneously at the boundaries of the current Earth’s climate and at the edges of their physiological tolerance, such as desert-adapted species. Modelling approaches alternatives to SDMs (e.g., hybrid SDMs) have been proposed as a better solution to tackle model extrapolation. These models should explicitly consider the species’ physiological thermal tolerance, producing outputs closer to the species’ ecology. We compared correlative SDMs with different extrapolation options (no-extrapolation, clamping, fade by clamping, full extrapolation) and hybrid SDMs incorporating species-specific thermal tolerances of mammals of the Arabian Pen..., , # Modelling species distribution at the boundaries of the Earth's climate ## Description of the data #### File: \"R_Code.R\" **Description:** The R code used to train the correlative Species distribution Models (SDMs), to run the data imputation of missing thermal tolerances values, and to train the hybrid SDMs. ### File: \"occurrences.csv\" **Description:** A dataframe containing the target species occurrences and the relative values of the predictors used to train the correlative SDMs. The columns are: **decimalLongitude:** the longitude in decimal degrees; **decimalLatitude:** the latitude in decimal degrees; **bio2:** the associated value of the mean diurnal temperature range, expressed in °C; **bio10:** the associated value of the mean temperature of the warmest quarter, expressed in °C; **gst:** the associated value of the mean temperature of the growing season, expressed in °C; **bio15:** the associated value of the precipitation seasonality, expressed in kg m^-2; **npp:...,