Efficacy of Spatial Land Change Modeler as a forecasting indicator for anthropogenic change dynamics over five decades: A case study of Shoolpaneshwar Wildlife Sanctuary, Gujarat, India

Abstract

Abstract Anthropogenic impacts cause Land use and land cover (LULC) changes that adversely disturb the protected area’s (PA). A quantitative evaluation of historical and future LULC changes over 50 years (1999–2049) in a highly exploited Shoolpaneshwar Wildlife Sanctuary (SWS), Gujarat, India is the primary objective of this study. Maximum likelihood classification (MLC) - a supervised classification technique was applied to classify LULC using Landsat 1999, 2009, and 2019 imagery. Land Change Modeler (LCM) embedded in IDRISI Terrset version 18.21 software incorporated with Multilayer perceptron (MLP) neural network and Markov chain with eight driver variables has been the centre for LULC monitoring, change assessment and future predictions. Classified LULC map for the year 1999, 2009 and 2019 show an overall accuracy with Kappa coefficient of 0.9879, 0.9625 and 0.9381 was 99.08%, 97.58% and 95.45% respectively. During 1999–2019, vegetation cover decreased from 29389.50 ha to 21207.35 ha while agricultural land increased from 28479.18 ha to 31920.66 ha respectively. The kappa indices (Kno, Klocation, and Kstandard) values are 0.9992, 0.9703, and 0.9493, respectively. The projected LULC map for 2029, 2039, and 2049 depicts that the vegetation cover will further degrade, while agricultural land would be increased. Overall, the study reveals that the anthropogenic interventions and intents would increase in the upcoming future, which will severely disturb the integrity of a diversity rich PA. This integrated approach of LULC modeling and remote sensing offers a reliable method for SWS management and planning; it recommends taking a few regulatory steps to moderate human-induced disturbances in SWS.