Classification and Assessment of the land use changes using Landsat satellite imagery (Case Study: Qazvin plan’s Aquifer)

One of the main issues in regional planning and development is land use change by human activities. It can be argued that human actions can lead to significant changes in current state of earth’s surface. Changes in surface cover (land cover change) may in turn lead to alternations in balance of energy, water, and geochemical fluctuations at local, regional or global levels. Land use mapping using remote-sensing data is one of the newest and most widely used methods for the provision of land use map, and making a comparison between the existent usages.Therefore, Considering the benefits and potentials of satellite data, this technology can be of great help in identifying and detecting these changes.

Processing satellite images and performing supervised classification helps to extract information from these images. This study was carried out for assess changes in  land-use from 1999 to 2019 in the Qazvin plan’s Aquifer. Qazvin plan’s Aquifer is located at the North West part of Iran and the Qazvin province. The land uses observed in visit the area included: 1-irrigated agricultural lands, 2-residential and industrial areas, 3-rangelands, 4-dry and abandoned lands and 5-salt-marsh and barren lands. In this study, ENVI 5.3 software was used for processing five selected imageries in this project (1999,2004,2009,2014 and 2019).For this purpose, Landsat-5 Thematic Mapper (1999, 2004, and 2009) and Landsat-8 Operation Land Imager Sensor (2014, and 2019) satellite images were used for the land use change analysis with 30-m spatial resolution, which were taken from the United States Geological Survey (USGS; https://glovis.usgs.gov/), and after correcting geometric and radiometric in the pre-processing stage, Maximum Likelihood Classification (MLC) algorithm as a supervised classification method has been used to identify and detect land use changes. Also, The overall accuracy test used to determine the accuracy of produced maps.

Detection of land use change is one of the most important applications of remote sensing data. The ability to periodically repeat over time, this data can be used to identify and investigate variable and dynamic phenomena in the environment. Different land use classes had been recognized and used as the base map. The result showed that, the area of rangeland lands has decreased from 1999 to 2019 and other uses have increased. so that the area of irrigated agricultural lands, residential and industrial areas, dry and abandoned lands and salt-marsh and barren lands have increased by 14.24%, 38.8%, 25.37% and 8.37%, respectively, but rangelands decreased by 21.16%. Overall accuracy and Kappa statistics were extracted from the error matrix. supervised classification accuracy for the 5 different time frames (1999,2004,2009,2014 and 2019) found from accuracy assessment showed that the highest accuracy was found for 2019 supervised classification (96.28% accuracy). Kappa value is also used to check accuracy in classification and having a Kappa value (0.81–1.00) denotes almost perfect match between the classified and referenced data. The Kappa coefficient for land use in 1999, 2004, 2009, 2014 and 2019 were 87%, 86%, 91%, 89%, and 94%, respectively. Also,The results showed that the extraction of adequate samples from different classes of land use would increase the possibility of correct distinction of image pixels received from the satellite and accurate extraction of land use classes. Thus, obtaining accurate results from the classification of images via the maximum likelihood method is depending on adequate and appropriate training samples.

The present study confirm that remote sensing is an important technology for extracting land use maps and detecting land use changes. Changes detection is made possible by this technology in less time and with better accuracy. Land use changes is one of the most important factors of environmental changes. Such changes is often the result of human intervention, in addition to the negative effects on the environment, will increase the damage to natural disasters. The quantification of land use changes is very useful for environmental management groups, policy makers and for public to better understand the surrounding. Hence, the researchers emphasize the need for the planning to managing natural resources and monitoring environmental changes.