| چکیده انگلیسی مقاله |
To assess environmental changes, monitoring systems and remote sensing satellites provide powerful tools that make the assessment of environmental change trends easier by multi-temporal comparisons. In recent decades, remote sensing data and GIS techniques for various aspects of urban spatial expansion and urban dispersal such as mapping (for expansion pattern), control (for process pattern recognition), measurement and evaluation (for analysis), and modeling (for Expansion simulation) are used. The object-based analysis is one of the emerging advanced techniques in the classification of satellite images. The object-oriented classification uses a segmentation process and a learning algorithm to analyze the spectral, spatial, and textural properties of the pixels. Along with the object-oriented classification method, Google Earth Engine, with extensive support for free satellite data and images, enables the classification and processing of high-speed satellite imagery that can be used in the monitoring and mapping land use. Methodology: In the present study, the digital data of the Landsat satellite provided by GEE are used. The data do not require pre-processing and initial correction (geometric, radiometric, etc.) and are readily available for processing. Landsat image types (1 to 8) can be summons with any processing level in GEE. In this study, atmospheric correction images of the Surface Reflectance Tier1 are used. This dataset is modified for atmospheric errors and includes OLI / TIRS sensors for Landsat 8. With simple coding patterns in GEE, the images of 1999, 2009, and 2019 are corrected for the processing step. GEE has provided a modern set of pixel-based classification that can be used for monitoring and mapping. By analyzing the corrected image of 1999, 2009, and 2019 and capturing the training samples, the images are classified with the support vector machine algorithms, random forest, and minimum distance. To perform object-oriented analysis and classification, images are segmented using the multiresolution segmentation algorithm in specialized recognition software. Geometric properties of land use classes (including shape, size, texture) are used for segmentation. By analyzing the results of the segmentation of images with different scale parameters, the optimal values of scale, shape, and compression for the images used are obtained. In this study, based on spatial resolution and image quality, four land use and land cover classes were considered in Zanjan urban areas. These classes include built-up, irrigated and urban green areas, dry farming, and rangelands. By selecting the above classes, training samples for multi-temporal images (1999, 2009, and 2019) are prepared. The nearest neighbor algorithm is used to classify images based on the object-oriented method. In this process, the maximum difference index of mean and NDVI vegetation index are also applied for each of the classes to reduce class mixing and improve the classification accuracy of influential parameters such as normalized difference built-up index (ndbi), mean and standard deviation of each band, area, the ratio of length to width, compaction, and brightness. Statistical parameters of kappa coefficients and overall accuracy are used for the accurate assessment of the classified images. To understand the changes in the area, after producing the land use maps and assessing them, the classification methods are used to evaluate the land use changes that occurred in the period 1999 to 2019. Discussion: After the classification of Landsat 5 and 8 satellite images, land use maps of 1999, 2009, and 2019 are prepared using object-oriented and pixel-based methods. Since in this study the parameters and characteristics of mean and standard deviation of bands, NDBI, NDVI indices, etc. are used to improve the results of the algorithm nearest neighbor object-oriented method, the results of image classification accuracy assessment show that the object-oriented method is weaker in separating rangelands and built-up in 1999 and 2009 than the support vector machine classification method. However, the object-oriented classification results for 2019 show the best performance of all the utilized classification algorithms. Due to the better results of the support vector machine classification method for 1999 and 2009 and the object-oriented method for 2019, the results of these methods are used in the assessment of land use changes in the study area. According to the results, significant changes have occurred in the region from 1999 to 2019. During this period, the land (mainly Zanjan) showed an increase of 5036 hectares. Also, the results show that Zanjan has grown and expanded into rangelands and dry farming in the suburbs over the period 1999 to 2019. Conclusion: Comparing the results of classifier accuracy assessment, the nearest neighbor object-oriented classification algorithm for 2019 showed better performance in terms of kappa coefficient and overall accuracy than other algorithms. Also, by comparing the results of the assessment of the classification maps of 1999 and 2009, the support vector machine algorithm showed the best performance compared to other classification algorithms in the study area. The support vector machine was the basis for the assessment of changes. Based on the results of land use changes assessment, in recent years, significant land use changes have occurred around Zanjan city. The reason for the increased land area in Zanjan in 2019 (26.12%) is the increase of population and the development of new settlements in the suburbs, and consequently, the reduction of agricultural rangelands. Keywords: Google Earth Engine, Object-Oriented, Support Vector Machine, Zanjan City. References: - Butt, A., Shabbir, R., Ahmad, S. S., & Aziz, N. (2015). Land Use Change Mapping and Analysis Using Remote Sensing and GIS: A Case Study of Simly Watershed, Islamabad, Pakistan. The Egyptian Journal of Remote Sensing and Space Science, 18(2), 251-259. - Campbell, J. B., & Wynne, R. H. (2011). Introduction to Remote Sensing. Guilford Press. - De Oliveira Silveira, E. M., De Menezes, M. D., Júnior, F. W. A., Terra, M. C. N. S., & De Mello, J. M. (2017). Assessment of Geostatistical Features for Object-Based Image Classification of Contrasted Landscape Vegetation Cover. Journal of Applied Remote Sensing, 11(3), 036004. - Dewan, A. M., & Yamaguchi, Y. (2009). Land Use and Land Cover Change in Greater Dhaka, Bangladesh: Using Remote Sensing to Promote Sustainable Urbanization. Journal of Applied Geography, 29(3), 390-401. - Dingle Robertson, L., & King, D. J. (2011). Comparison of Pixel-and Object-Based Classification in Land Cover Change Mapping. International Journal of Remote Sensing, 32(6), 1505-1529. - El-Asmar, H. M., Hereher, M. E., & El Kafrawy, S. B. (2013). Surface Area Change Detection of the Burullus Lagoon, North of the Nile Delta, Egypt, Using Water Indices: A Remote Sensing Approach. The Egyptian Journal of Remote Sensing and Space Science, 16(1), 119-123. - Esam, I., Abdalla, F., & Erich, N. (2012). Land Use and Land Cover Changes of West Tahta Region, Sohag Governorate, Upper Egypt. Journal of Geographic Information System, 4(06), 483. - Feizizadeh, B., Blaschke, T., Nazmfar, H., Akbari, E., & Kohbanani, H. R. (2013). Monitoring Land Surface Temperature Relationship to Land Use/Land Cover from Satellite Imagery in Maraqeh County, Iran. Journal of Environmental Planning and Management, 56(9), 1290-1315. - Ghebrezgabher, M. G., Yang, T., Yang, X., Wang, X., & Khan, M. (2016). Extracting and Analyzing Forest and Woodland Cover Change in Eritrea Based on Landsat Data Using Supervised Classification. The Egyptian Journal of Remote Sensing and Space Science, 19(1), 37-47. - Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-Scale Geospatial Analysis for Everyone. Journal of Remote Sensing of Environment, 202, 18-27. - Huo, L. Z., Boschetti, L., & Sparks, A. M. (2019). Object-Based Classification of Forest Disturbance Types in the Conterminous United States. Journal of Remote Sensing, 11(5), 477. - Im, J., Jensen, J. R., & Tullis, J. A. (2008). Object‐Based Change Detection Using Correlation Image Analysis and Image Segmentation. International Journal of Remote Sensing, 29(2), 399-423. - Lillesand, T., Kiefer, R. W., & Chipman, J. (2015). Remote Sensing and Image Interpretation. John Wiley & Sons. - Ma, L., Li, M., Ma, X., Cheng, L., Du, P., & Liu, Y. (2017). A Review of Supervised Object-Based Land-Cover Image Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 130, 277-293. - Mahmoudi, F. T., Samadzadegan, F., & Reinartz, P. (2014). Object Recognition Based on the Context Aware Decision-Level Fusion in Multiviews Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(1), 12-22. - Rawat, J. S., & Kumar, M. (2015). Monitoring Land Use/Cover Change Using Remote Sensing and GIS Techniques: A Case Study of Hawalbagh Block, District Almora, Uttarakhand, India. The Egyptian Journal of Remote Sensing and Space Science, 18(1), 77-84. - Shelestov, A., Lavreniuk, M., Kussul, N., Novikov, A., & Skakun, S. (2017). Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping. Journal of Frontiers in Earth Science, 5, 17. - Weih, R. C., & Riggan, N. D. (2010). Object-Based Classification vs. Pixel-Based Classification: Comparative Importance of Multi-Resolution Imagery. The International Archives of the Photogrammetry, Remote Sensing, and Spatial Information Sciences, 38(4), C7. - Weng, Q. (2012). Remote Sensing of Impervious Surfaces in the Urban Areas: Requirements, Methods, and Trends. Journal of Remote Sensing of Environment, 117, 34-49. - Whiteside, T. G., Boggs, G. S., & Maier, S. W. (2011). Comparing Object-Based and Pixel-Based Classifications for Mapping Savannas. International Journal of Applied Earth Observation and Geoinformation, 13(6), 884-893. - Yan, G., Mas, J. F., Maathuis, B. H. P., Xiangmin, Z., & Van Dijk, P. M. (2006). Comparison of Pixel‐Based and Object‐Oriented Image Classification Approaches—a Case Study in a Coal Fire Area, Wuda, Inner Mongolia, China. International Journal of Remote Sensing, 27(18), 4039-4055. - Zha, Y., Gao, J., & Ni, S. (2003). The Use of Normalized Difference Built-Up Index in Automatically Mapping Urban Areas from TM Imagery. International Journal of Remote Sensing, 24(3), 583-594. |