همکاری با انجمن علمی مدیریت و کنترل مناطق بیابانی ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه آزاد اسلامی، واحد جیرفت، کرمان، ایران

2 دانشجوی دکتری بیابان‌زدایی، دانشکده منابع طبیعی و کویر شناسی، دانشگاه یزد، ایران

3 عضو هیات علمی دانشکده منابع طبیعی، دانشگاه یزد، ایران

چکیده

به دلیل افزایش جمعیت و در نتیجه افزایش نیاز به غذا، طی دهه‌های گذشته شاهد تغییرات گسترده در کاربری اراضی و به‌ویژه افزایش اراضی کشاورزی هستیم. هدف از این تحقیق، بررسی تغییرات کاربری اراضی دشت برتش در شهرستان دهلران استان ایلام طی دوره 26 ساله (1367 تا 1393) با استفاده از روش شیءگرا می‌باشد. برای انجام این تحقیق، پس از تهیه تصاویر ماهواره لندست سنجنده TM (1988)، ETM+ (2001) و لندست 8 (2014)، تصحیحات مورد نیاز انجام شد و بعد با استفاده از روش شیءگرا، نقشه کاربری اراضی مربوط به سه دوره زمانی تهیه گردید. نتایج حاصل از ارزیابی دقت نقشه‌های تولید شده نشان می‌دهد که بیشترین میزان دقت کل و ضریب کاپا با مقدار 90 و 95 درصد مربوط به تصویر سال 2001 و کمترین آن با مقدار 80 و 90 درصد مربوط به تصویر سال 1988 می‌باشد. دقت کل و ضریب کاپا در تصویر سال 2014 نیز با مقدار 90 و 92 درصد، دقت خوبی را به نمایش می‌گذارد. نتایج روند تغییرات کاربری اراضی نشان داد که کاربری مرتع متوسط با کاهش بیش از 21 هزار هکتاری، بیشترین تغییرات را داشته است. در رتبه ‌بعدی، اراضی کشاورزی قرار دارد که افزایش بیش از 15 هزار هکتاری (دو برابری) را نشان می‌دهد، که دلیل آن افزایش جمعیت و وجود منابع آبی کافی در این ناحیه می‌باشد. کاربری مرتع فقیر نیز روند افزایشی حدود 5/1 برابری را نشان می‌دهد که نشان‌دهنده تخریب مراتع متوسط می‌باشد. اراضی شوره‌زار نیز در ابتدا روند افزایشی، اما در ادامه به دلیل تبدیل شدن به اراضی کشاورزی، روند کاهشی را نشان می‌دهد. میزان دقت کل (90-900) و ضریب کاپا (95-90) نشان‌دهنده دقت بسیار بالای این روش در تعیین کاربری اراضی می‌باشد.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluating trend Change Land Use / Cover Using Remote Sensing Technique and Object-Oriented Classification Algorithm (Case study: Bartash Plain in Dehloran, Ilam)

نویسندگان [English]

  • Ali Khenamani 1
  • Hasan Fathizad 2
  • Mohamad Ali Hakimzadeh 3

1 Jiroft Branch, Islamic Azad University,Kerman, Iran

2 PhD student of Combat Desertification, Department of Natural resources and Desert Studies, Yazd University, Iran

چکیده [English]

     Over the past decades, due to increased population and consequent increase in the need for food, we have seen extensive changes in land use, and in particular, the increase of agricultural lands. The aim of this study was to evaluate the changes in land use in the Bartash plain in Dehloran city of Ilam province during 26 years from 1988 to 2014 using the object-oriented approach. To accomplish this research, the necessary corrections were made after the acquisition of Landsat TM (1988), ETM + (2001) and Landsat 8 (2014) satellite images, and then, using the object-oriented method, the land use map was prepared for the three time periods. The results of the evaluation of the accuracy of the produced maps show that the highest accuracy and Kappa coefficient with the values of 90 and 95% correspond to the image of 2001, and the lowest them with the value of 80 and 90% was related to the image of 1988. Total accuracy and Kappa coefficient in the image of 2014 with 90% and 92%, respectively show a good accuracy. The results of land use change trend showed that the land use of the fair rangeland had the most changes with a decrease of more than 21 thousand hectares. Agricultural lands are in the next place, showing an increase of over 15,000 hectares (twofold) that could be due to the increase in population and the availability of adequate water resources in this area. The land use of poor rangelands also shows an increasing trend of 1.5 fold, indicating the degradation of fair rangelands. The saline lands initially show an increasing trend but then show a decreasing trend due to converting to agricultural lands. The overall accuracy (900-90) and kappa coefficient (95-90) indicate the high accuracy of this method in determining the land use.

کلیدواژه‌ها [English]

  • land use
  • total accuracy
  • Kappa coefficient
  • Segmentation
  • Bartash plain
-  Arekhi, S., 2015. Detecting changes cover / land use with object-oriented processing satellite images using the software Idrisi Selva (Case study: Abdanan). Journal of Geographic Information, 24: 51-61.
-  Baatz, M. and Schape, A., 1999. Object-oriented and multi-scale image analysis in semantic network, in Proc. 2nd Int. symposium on operalization of remote sensing, Ensched, ITC, 148-157.
-  Blaschke, T., 2010. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65: 2–16.
-  Blaschke,T., 2009. Object based image analysis for remote sensing, ISPRS Journal of Photogrammetry and Remote Sensing, journal homepage: www.elsevier.com/locate/isprsjprs.pp.10-21.
-  Breiman, L., 2001. Random forests. Mach. Learn, 45: 5–32.
-  Brenning, A., 2009. Benchmarking classifiers to optimally integrate terrain analysis and multispectral remote sensing in automatic rock glacier detection. Journal of remote sensing environmental. 113(1): 239–247.
-  Carreiras, J. M. B., Pereira, J. M. C., Campagnolo, M. L. and Shimabukuro, Y. E., 2006. Assessing the extent of agriculture/pasture and secondary succession forest in the Brazilian legal Amazon using SPOT VEGETATION data. . Journal of Remote Sensing Environmental, 101(3): 283–298.
-  Defniens Imaging Gmb, H., 2006. Defniens Professional 5 User Guide. http://www.defniens.com./user guide .pdf, 249p.
-  Dragut, L. and Eisank, C., 2011. Object representations at multiple scales from digital elevation models. Journal of Geomorphology, 129: 183–189.
-  Feizizadeh, B. and Halali, H., 2009. Comparison of pixel-based, object-oriented and effective parameters on the classification of land use / land covers in West Azerbaijan province. Journal of Applied Geography, 71: 73-84.
-  Feizizadeh, B., Jafari, F. and Nazmfar, H., 2008. The use of remote sensing data to detect changes in urban land use. The Journal of Fine Arts, 34: 31-20.
-  Feizizadeh, B., Pirnazar, M., Zandkarimi, A. and Abedi Gheshlaghi, H., 2015. Evaluate the use of fuzzy algorithms in increasing the accuracy of land use maps derived by processing methods object-oriented. Journal of Geographic Information, 24: 107-117.
-  Gislason, P. O., Benediktsson, J. A. and Sveinsson, J. R., 2006. Random forests for land cover classification. Journal of Pattern Recognition Letters. 27(4): 294–300.
-  Haudhuri, B. and Sarkar, N., 1995. Texture segmentation using fractal dimension. Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, 17: 72– 77.
-  Hofmann, T., Puzicha, J. and Buhmann, J., 1998. Unsupervised texture segmentation in a deterministic annealing framework. Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, 20: 803-818.
-  Huang, C., Davis, L. S. and Townshend, J. R. G., 2002. An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4): 725–749.
-  Huang, L. and Ni. L., 2008. Object-oriented classification of high resolution satellite image for better accuracy, Proceedings of the 8th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Shanghai, China, June, 25-27, 211-218.
-  Jain, A. and Farrokhnia, F., 1991. Unsupervised texture segmentation using Gabor filters. Journal of Pattern Recognition. 24(12): 1167-1186.
-  Linke, J. and McDermid, G., 2011. A conceptual model for multi-temporal landscape monitoring in an object-based environment. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 4(2): 265–271.
-  Lu, D., Mausel, P., Brondizio, E. and Moran, E., 2004. Change detection techniques. International Journal of Remote Sensing, 25(12): 2365-2401.
-  Matinfar, H. R., Sarmadian, F., Alavipanah, S. K. and Heck, R., 2008. Characterizing Land use/land cover types by Landsat 7 data based upon Object oriented approach in Kashan region, Iranian journal of Range and Desert Research, 14(4): 589-602.
-  Mori, M., Hirose, Y. and Akamatsu, Y. L., 2003. Object- based classification of Ikonos data for rural land use mapping. Cognition Applied Notes, 5(1).
-  Myint, S. W., Gober, P., Brazel, A., Grossman-Clarke, S. and Weng, Q., 2011. Per-pixel vs. object-based classification of urban land covers extraction using high spatial resolution imagery. Journal of Remote Sensing of Environment. 115(5): 1145-1161.
-  Otukei, J. R. and Blaschke, T., 2010. Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms. International Journal of Applied Earth Observation, 12: 27–31.
-  Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1): 217–222.
-  Parker, D. C., Manson, S. M., Janssen, M. A., Hoffmann, M. J. and Deadman, P., 2003. Multi agent systems for the simulation of land use and land cover change. Journal of Annals of the American Association of Geographers, 43: 314–337.
-  UNEP., 1991. Status of desertification and implementation of the United Nations plan of action to combat desertification. Nairobi, Kenya.
-  Van Den Eeckhaut, M., Kerle, N., Poesen, J. and Hervás, J., 2012. Object-oriented identification of forested landslides with derivatives of single pulse LiDAR data.Journal of Geomorphology, 173–174: 30–42.
-  Yaghobzadeh, M. and Akbarpour, A., 2011. The effect of satellite image classification algorithm based on curve number runoff and maximum food discharge using GIS and RS, Journal of Geography and Development, 9(22): 5-22.
Yan, G., 2003. Pixel based and object oriented Image for coal fire research. http://www.ITC.com (accessed in July 2008). 3-99.