Document Type : Research Paper

Authors

• elhame ebady ¹
• Fariba Esfandayari Darabad ²
• sayyad Asghari ³
• Raoof Mostafazadeh ⁴
• Elham mollanuri ⁵

¹ PhD student of Mohaghegh Ardabili University

² Professor, Department of physical Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Iran

³ Professor, Department of Physical Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Iran

⁴ Associate Professor, Department of Natural Resources, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili

⁵ Master's degree in Department of Natural Geography, Mohaghegh Ardabili University, Ardabil, Iran

Abstract

One of the important conditions for optimal use of land is obtaining information about landuse patterns and their changes over time. Landuse is usually defined based on human use of land, emphasizing the role of land in economic activities. Today, remote sensing technology is considered as the main element in landuse monitoring. The aim of the current research is to extract landuse maps for the years 2000 and 2021 in FirozabadKhalkhal region and to investigate the changes made in the studied time period in the region using the images of ETM and OLI sensors of Landsat. Also, checking the capability of basic pixel and object-oriented methods for landuse classification is another purpose of this study. In the current research, the object-oriented technique nearest neighbor algorithm and the vector machine method supporting the pixel-based algorithm have been used for landuse classification. Then, to verify the accuracy of these two methods, the overall accuracy and Kappa were extracted. The results of this evaluation show the high accuracy of the object-oriented method in extracting land use classes. Based on the results of the detection of landuse changes in the studied time period, the highest amount of changes occurred is related to the use of good pasture to poor pasture with a value of 51.72 square kilometers, followed by forest to good pasture with a value of 30.11 and the lowest changes It is related to the use of pasture and water with the amount of 0.03 square kilometers. The reasons for these changes are the increase in population, indiscriminate grazing of livestock, incorrect and illegal use of different lands. The use of more parameters such as scale, shape, compactness, color, texture, smoothness criterion and pattern for landuse classification in the object oriented technique can be considered as an innovation of the present study.

Highlights

One of the important conditions for optimal use of land is obtaining information about land use patterns and their changes over time. Land use is usually defined based on human use of land, emphasizing the role of land in economic activities. Today, remote sensing technology is considered as the main element in land use monitoring. The aim of the current research is to extract land use maps for the years 2000 and 2021 in Firozabad Khalkhal region and to investigate the changes made in the studied time period in the region using the images of ETM and OLI sensors of Landsat satellite. Also, checking the capability of basic pixel and object-oriented methods for land use classification is another goal of this study. In the current research, the object-oriented technique s nearest neighbor algorithm and the vector machine method supporting the pixel-based algorithm have been used for land use classification. Then, to verify the accuracy of these two methods, the overall accuracy and Kappa coefficient were extracted. The results of this evaluation show the high accuracy of the object-oriented method in extracting land use classes. Based on the results of the detection of land use changes in the studied time period, the highest amount of changes occurred is related to the use of good pasture to poor pasture with a value of 51.72 square kilometers, followed by forest to good pasture with a value of 30.11 and the lowest changes It is related to the use of pasture and water with the amount of 0.03 square kilometers. The reasons for these changes can be the increase in population, climate changes and precipitation fluctuations and temperature increase. The use of more parameters such as scale, shape, compactness, color, texture, smoothness criterion and pattern for land use classification in the object oriented technique can be considered as an innovation of the present study.

Keywords

• Object oriented
• support vector machine
• nearest neighbor
• land use

10.22034/gp.2023.52092.3014

Main Subjects

• Geomorphology