ISPRS-Archives The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS-Archives Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2194-9034 Copernicus Publications Göttingen, Germany 10.5194/isprs-archives-XLII-4-W18-1159-2019 INVESTIGATING OF FOREST CHANGE IN GOLESTAN PROVINCE USING LANDSAT IMAGE Zoraghi M. 1 Saadi R. 1 Hasanlou M. https://orcid.org/0000-0002-7254-4475 1 School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Iran 19 10 2019 XLII-4/W18 1159 1162 Copyright: © 2019 M. Zoraghi et al. 2019 This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/ This article is available from https://isprs-archives.copernicus.org/articles/XLII-4-W18/1159/2019/isprs-archives-XLII-4-W18-1159-2019.html The full text article is available as a PDF file from https://isprs-archives.copernicus.org/articles/XLII-4-W18/1159/2019/isprs-archives-XLII-4-W18-1159-2019.pdf

In recent years, forests in the north of the country have been attacked due to human interference. Increasing population and development of residential and agricultural areas have led to deforestation. Change detection is one of the most common methods for evaluating natural resources. The aim of this study is to monitor changes in forests of Golestan province in two period times from 1990 to 2019, using Landsat images. Accordingly, by incorporating those data sets land use maps are produced. Also, the SVM algorithm is used with six different classes including forest (F), urban area (U), agriculture (A), uncultivated land (UL), water (w) and bare soil (BS). The achieved overall accuracies are 85.48% and 89.86%. Then the map and matrix changes were obtained by post-classification comparison method. The results showed that the Golestan province's forests were reduced and converted to agricultural and urban land uses.