Ecological niche modelling of Indigofera oblongifolia (Forssk.): a global machine learning assessment using climatic and non-climatic predictors

Abstract Climate change and other extinction facilitators have caused significant shifts in the distribution patterns of many species during the past few decades. Restoring and protecting lesser-known species may be more challenging without adequate biogeographical information. To address this knowledge gap, the current study set out to determine the global spatial distribution patterns of Indigofera oblongifolia (Forssk) a relatively lesser-known leguminous species. This was accomplished by utilizing three distinct bioclimatic temporal frames (current, 2050, and 2070) and four greenhouse gas scenarios (RCPs 2.6, 4.5, 6.0, and 8.5), in addition to non-climatic predictors such as global livestock population, human modification of terrestrial ecosystems, and global fertilizers application (nitrogen and phosphorus). Furthermore, we evaluate the degree of indigenousness using the geographical area, habitat suitability categories, and number of polygons. This research reveals that climatic predictors outperform non-climatic predictors in terms of improving model quality. Precipitation Seasonality is one of the most important factors influencing this species' optimum habitat suitability up to 150 mm for the current, 2050 RCP 8.5 and 2070-RCPs 2.6, 4.5, and 8.5. Our ellipsoid niche modelling extends the range of precipitation during the wettest quarter and maximum temperature during the warmest month to 637 mm and 26.5–31.80 degrees Celsius, respectively. India has a higher indigenous score in the optimal class than the African region. This findings suggest that the species in question tends to occupy contiguous regions in Africa, while in India, it is dispersed into several smaller meta-populations.