Rahul Raveendran Nair, Gudasalamani Ravikanth & Punnakkal Sreedharan Udayan

Tropical Ecology |  February 13, 2024

Considering the medicinal and conservational significance of Saraca asoca, the present study employed three different geographical ranges for building ecological niche models. The vifstep procedure detected multicollinearity among 10 out of 19 predictor variables. The selected subset included mean diurnal range, isothermality, mean temperature of wettest quarter, mean temperature of driest quarter, annual precipitation, precipitation of driest month, precipitation seasonality, precipitation of warmest quarter, and precipitation of coldest quarter. The performances of machine learning and regression approaches were compared. Machine learning algorithm RF outweighed all other algorithms in performance.