Detection of Land Use Changes in Forests Using Satellite Image Classification Based on Deep Learning: A Case Study of Sardasht Forests

Abstract

Awareness of changes in forest areas has always been one of the most crucial environmental considerations globally. Sardasht forests is located in the northern Zagros region and with an area of around 91,117 hectares constitute for 24% of Iran total forests. They play an important role in water supply, soil preservation, climate regulation and overall economic and social balance in the country. Nevertheless, these forests are currently perceived as degraded due to the primary reason of tree cutting for fuel and livestock feed. In this study, remote sensing data of the study area including Landsat 5 TM satellite images from 2002, Landsat 7 ETM images from 2012, Landsat 8 OLI images 2020 and classification algorithms, maximum likelihood and artificial neural network were utilized. To examine the accuracy of each classification, ground truth points were randomly collected using GPS devices and by implementing control points, statistical parameters of error accuracy including Kappa coefficient and overall accuracy were calculated. The results show that the map generated using the artificial neural network algorithm has an overall accuracy of 98.32% with a Kappa coefficient of 0.9781 while the map produced by the maximum likelihood algorithm has an overall accuracy of 92.45% with a Kappa coefficient of 0.901. As a result, the artificial neural network algorithm demonstrates to be a more suitable method for producing land cover maps compared to the maximum likelihood algorithm.