Forest cover dynamics analysis and prediction modeling using logistic regression model

•The change in forest cover was predicted using logistic regression model (LRM).•Explanatory variables (EV) associated with forest conversion process were analyzed.•Distance from forest edge, roads, settlements and slope position classes were the EV.•Highest regression coefficient (β=−26.892) was observed for distance from forest edge.•The LRM modeled forest conversion by predicting forest cover with high accuracy (ROC=87%). Forest cover conversion and depletion are of global concern due to their role in global warming. The present study attempted to study the forest cover dynamics and prediction modeling in Bhanupratappur Forest Division of Kanker district in Chhattisgarh province of India. The study aims to examine and analyze the various explanatory variables associated with forest conversion process and predict forest cover change using logistic regression model (LRM). The forest cover for the periods 1990 and 2000, derived from Landsat TM satellite imagery, was used to predict the forest cover for 2010. The predictive performance of the model was assessed by comparing the model-predicted forest cover with the actual forest cover for 2010. To explain the effects of anthropogenic pressure on forest, this study considered three distance variables viz., distance from forest edge, roads and settlements, and slope position classes as explanatory variables of forest change. The highest regression coefficient (β=−26.892) was noticed in case of distance from forest edge, which signifies the higher probability of forest change in areas that are closer to the forest edges. The analysis showed that forest cover has undergone continuous change between 1990 and 2010, leading to the loss of 107.2km2 of forest area. The LRM successfully predicted the forest cover for the period 2010 with reasonably high accuracy (ROC=87%).