پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 161 |
| تعداد شماره‌ها | 6,532 |
| تعداد مقالات | 70,502 |
| تعداد مشاهده مقاله | 124,117,392 |
| تعداد دریافت فایل اصل مقاله | 97,222,935 |
بررسی کارائی روش‌های طبقهبندی تصاویر ماهواره‌ای در پایش تغییرات پوشش اراضی(مطالعة موردی: حوضۀ آبخیز شهرکرد، چهارمحال و بختیاری) | ||
| نشریه علمی - پژوهشی مرتع و آبخیزداری | ||
| مقاله 10، دوره 71، شماره 3، آذر 1397، صفحه 699-714 اصل مقاله (1.75 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22059/jrwm.2018.244032.1177 | ||
| نویسندگان | ||
| الهه ظفریان1؛ عطاالله ابراهیمی* 2؛ رضا امیدی پور3 | ||
| 1کارشناسی ارشد مرتعداری، دانشکده منابع طبیعی و علوم زمین، دانشگاه شهرکرد. | ||
| 2دانشیار گروه مرتع و آبخیزداری، دانشکده منابع طبیعی و علوم زمین، دانشگاه شهرکرد. | ||
| 3دانشجوی دکترای علوم مرتع، دانشکده منابع طبیعی و علوم زمین، دانشگاه شهرکرد. | ||
| چکیده | ||
| تهیة نقشة پوشش اراضی، از مهمترین منابع اطلاعاتی مدیریت منابعطبیعی محسوب می‌شود. از تصاویر ماهواره‌ای می‌توان نقشه‌های پوشش اراضی را استخراج کرد. گوناگونی در روش‌های طبقهبندی تصاویر ماهواره و انتخاب بهترین روش، یکی از مهمترین مشکلات در استفاده از این ابزار کاربردی می‌باشد. بنابراین، در این تحقیق، به منظور بررسی روند تغییرات پوشش اراضی حوضۀ آبخیز شهرکرد، ابتدا کارآیی روش‌های طبقهبندی حداکثراحتمال، شئ‌گرا و شبکة عصبی مصنوعی ارزیابی و سپس روند تغییرات پوشش اراضی حوضۀ آبخیز شهرکرد در سال‌های 1378، 1387 و 1394 با استفاده از تصاویر لندست TM، ETM+ و OLI بررسی شد. پس از تصحیحات هندسی و رادیومتریک و طبقهبندی، نقشة پوشش اراضی سال 1394 بر اساس سه روش مذکور تهیه گردید. نتایج ارزیابی صحت نقشه‌های تولیدی سال 1394 نشان داد که روش شئ‌گرا در هر دو شاخص صحت کل و ضریب کاپا (به ترتیب 93 و 90%)، دقیق‌تر از دو روش دیگر بوده است. بنابراین، با روش شئ‌گرا روند تغییرات پوشش اراضی بررسی شد. نتایج بررسی روند تغییرات نشان داد که در طول دورة آماری، مناطق مسکونی از 72/1 درصد در سال 1378 به 98/2 درصد در سال 1394 و اراضی کشاورزی نیز در همین دوره از 73/5 درصد به 60/12 درصد افزایش یافته ولی مراتع با کاهش 05/9 درصدی در کل دوره و اراضی بایر در دورة اول (1378-1387) با افزایش 19/6 درصدی و در دورة دوم (1387-1394) با کاهش 27/5 درصدی مواجه بودند. نتیجة حاصل از این تحقیق، نشان داد که طبقهبندی شئ‌گرا نسبت به روش‌های پیکسل پایه برای ارزیابی تغییرات پوشش اراضی ارجحیت دارند. | ||
| کلیدواژه‌ها | ||
| سنجش از دور؛ تهیة نقشة پوشش اراضی؛ حداکثر احتمال؛ روش شئ‌گرا؛ شبکة عصبی مصنوعی؛ حوضۀ آبخیز شهرکرد | ||
| عنوان مقاله [English] | ||
| Evaluation of the Efficiency of Satellite Imagery Classification Approaches in Monitoring of Land Cover Changes (Case Study: Shahrekord Basin, Chaharmahal va Bakhtiari) | ||
| نویسندگان [English] | ||
| elahe zafarian1؛ Ataollah Ebrahimi2؛ Reza Omidipour3 | ||
| 1M.Sc in Rangeland Management / Faculty of Natural Resources and Earth Science, Department of Rangeland and Watershed Management, Shahrekord University | ||
| 3Ph.D. Student / Shahrekord University, Faculty of Natural Resource and Earth Science/ Department of Range and Watershed Management | ||
| چکیده [English] | ||
| Land cover mapping is essential for natural resource management. Satellite imagery can be used for mapping land cover. Several methods are available for land cover mapping whilst choosing the best method is one of the most important issue in this context. To compare pros and cons of three methods of classification including maximum likelihood, object-based segmentation and artificial neural network, first, the efficiency of these three methods were evaluated. Then the trend of land cover changes in Shahrekord basin was investigated for 1999, 2009 and 2015 using Landsat images of TM, ETM+ and OLI sensors, respectively. After geometric and radiometric corrections, the land cover map of 2015 was prepared based on the three methods. The results of the validation mapping methods revealed that object-based method was more promising than the others with 93 and 90% for total accuracy and Kappa coefficients of agreement, respectively. So, the object-based segmentation method is recommended for monitoring of land cover changes. The results of the land cover change indicated that residential areas increased from 1.727% in 1999 to 2.98% in 2015 and agricultural lands increased from 5.73% to 12.60% but rangelands were decreased by 9.05 in total. Moreover, bare-lands were increased from 1999 to 2009 by 6.19% but decreased from 2009 to 2015 by 5.27%. The result of this study showed that the object-based method is superior to pixel based method of Maximum-liklihood and neural network. So, object-based segmentation is recommended for estimating land cover changes. | ||
| کلیدواژه‌ها [English] | ||
| Remote Sensing, Land Cover Mapping, Maximum Likelihood, Object-based segmentation, Artificial Neural Network, Shahrekord Basin | ||
| مراجع | ||
|
[1] AlaviPanah, S. K. And Massoudi, M. (1996). Preparation of land use map using Landsat satellite digital data and geographic information systems in a case study of Fars Muk area. Journal of Agricultural Science and Natural Resources, (no. 7), p. 76-65. [2] AlaviPanah, S K. (2003). Application of Remote Sensing in Earth Sciences (Soil Science). University of Tehran Institute, 478 pages. [3] Amiri, A., Chavoshi, H. And Amini, C. (2007). (Quickbird) Comparison of three methods of fuzzy classification, neural network and least distance in satellite imagery. Geomatics Conference 86, Tehran, Mapping Organization of Iran. [4] Arekhi, s., gerayi, p. and Arekhi, M. (2008). Evaluation of Land Use Change Process in Kabir Kouh Protected Area Using RS and GIS. (Case Study: Ilam Province), Geomatics Conference 87, Tehran, Mapping Organization of Iran. [5] Benediktsson J. A., Swain P. H. and Esroy, O. K. (1990). Neural network approaches versus statistical methods in classification of multisource remote sensing data. IEEE Trans. Geosci. Remote Sens. 28: 540-552. [6] Blaschke, T. (2006). Object based image analysis for remote sensing. ISPRS journal of photogrammetry and remote sensing, 65(1), 2-16. [7] 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. [8] Coppin, P. I.,Jonckheere, K., Nackaerts, Muys, B., 2004. Digital change detection methods in ecosystem monitoring: a review. Remote Sensing, 25 (9), 1565–1596. [9] Duro D. C., Franklin S. E and . Dubé M. G. (2012). A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sensing of Environment, 118: 259-272. [10] Feizizadeh B., AAzizi. H And Valizadeh. K. (2007). Extraction of land use in Malekan city using Landsat satellite images. 7. Amiyah Journal. Volume III. Islamic Azad University of Malayer. [11] Feizizadeh, B. And Haji Mirrahimi, M. (2008). Detection of Land Use Change Using Object-Oriented Classification (Case Study: Andisheh Township). Geomatics Congress 87, Tehran, Mapping Organization of Iran. [12] Feizizadeh, B., Jaafari, F. And Nazmfar, H. (2008). Application of Remote Sensing Data in Detection of Land Use Change Changes. Fine Arts, Vol. 34, No. 20. [13] Foody, G. M. (2000). Mapping Land Cover from Remotely Sensed Data with a Softened Feedforward Neural Network Classification. Intelligent and Robotic. [14] Gao, Y., Mas, J. F., and Navarrete, A. (2009). The improvement of an object-oriented classification using multi-temporal MODIS EVI satellite data. International Journal of Digital Earth, 2(3), 219-236. [15] Gahegan M., German G and West G. (1999). Improving Neural Network Performance on the Classification of Complex Geographic Datasets. Jurnal of Geographical Systems, 1: 3-22 [16] Ghadami, M., Aligolizadeh, N. And Brady Annamaddinhad, R. (2010). Investigating the Role of Tourism in Land Use Change (Case Study: Central District of Nowshahr). Urban and Regional Studies, First Year, (No. 3), pp. 21-42. [17] Karimi, H., Omidipour, R., Omidi, A. (2013). Study of Ilam City Development Using Remote Sensing for Urban Planning and Management. First International Conference on Urban Development, Sanandaj, 1-8. [18] Khosravi, A. And Momeni, M. (2012). Extracting residential buildings from high resolution images using the definition of rules in the object classification classification. 4th Iranian Conference on Electrical and Electronic Engineering, Islamic Azad University of Gonabad, 1944-1937. [19] Liu X.H, Skidmore A.K and Oosten H.V.( 2002) Integration of Classification Methods for Improvement of Land-cover Map Accuracy, ISPRS Journal of Photogrammetry and Remote Sensing, No.56, pp. 257-268. [20] Lopez, E., Bocco, G., Menduza, M., Valezquez, A., Aguirre Rivera, J. R. (2005). Peasant emigration and land-use change at the watershed level: A GIS-based approach in Central Mexico. Agricultural Systems, pp. 62-78. [21] Lotfi. P., Mahmoud Zadeh. H. Abdullahi. M And SalekFarokhi. R. (2010). Application of satellite images of Spot for mapping of land use in Marand city with the Objective approach. Journal of Remote Sensing and Geographic Information Systems in Scheduling Quarterly Journal, Year 1, No. 2, pp. 47-56. [22] Mertens B and Lambin E.F. (2000). Land Cover Change Trajectories In Southern Cameroon. Analysis of Association of American Geographers, 3: 467-494. [23] Mori M., Hirose Y. and Akamatsu Y. L. (2003). Object- nased classification of Ikonos data for rural land use mapping. Http://www.define.com. eCognition Applied Notes , Vol 5 , No. 1 [24] Platt R. V and Schoennagel T. (2009). An object-oriented ap-proach to assessing changes in tree cover in the Colorado Front Range 1938–1999, Forest Ecology and Management 258 (2009). Pages 1342–1349, journal homepage: www.elsevier.com/locate/ foreco. [25] Omidipour, R., Moradi, H. And Arekhi, S. (2013). Comparison of Basic and Object Oriented Pixel Classification Methods for Land Use Mapping Using Satellite Data. Remote Sensing and GIS Iran, 5 (No. 3), p. 110-99. [26] Rafiyan, A., DarvishSefat, A., Babaie, S And Metaji, A. (2010). Evaluation of Pixel Classifications and Ground Base Aerial Images for Tree Species (Case Study: Chamestan Nour Forestry). Forest Journal of Iran, Iranian Forestry Association. Third Year, (No. 1), pp. 47-35. [27] Rafiyan, A., DervishSefat, A., Babaei Kafafi, S. and Metaji, A. (2011). Evaluation of base pixel classifications and aerial image object for tree species detection (Case study: Chamestan Nour Forestry). Forest Journal of Iran, Year 3, Issue 1, Page 35 to 47. [28] RezaiMoqaddam, M., Rezaibnfshha, M., Faizizadeh, B. And Nazmfar, H. (2010). Land Cover / Land Use Classification Based on Objective Technique and Satellite Images, Case Study: West Azarbaijan Province. Watershed research, No. 87, p. 21 to 35. [29] Salman Mahini. A., Feqhi J., Nadali A. and Riazi, B. (2008). Investigation of Golestan Province Coverage Changes by Artificial Neural Network Classification Using TM and ETM + Land Data Systems. Journal of Forest and Poplar, Volume 16, Issue 3. [30] Shetaii S, and Abdi O. (2008). Mapping of land use in mountainous regions of Zagros using ETM+ data. Agricultural Sciences and Natural Resources university of Gorgan, Gorgan., 57: 129-138. [31] Singh A. (1986). Change detection in the tropical forest environment of northeastern India using Landsat. Remote sensing and tropical land management, 237-254. [32] Statistical Yearbook. (2013). Chaharmahal & Bakhtiari Province. Statistical Center of Iran. [33] Taze, M and Khalili Samani, N. (2013). Study of Land Use Change Changes in Shahrekord County Using Remote Sensing Technique (1976 to 2055), First National Conference on the Environment, Energy and Biological Defense, Tehran, Mehr Arvand Higher Education Institution, Promotion Group for Environmental Lovers. [34] Wang Z, Wei W, Zhao S and Chen X. (2004) Object-oriented classification andapplication in land use classification using SPOT-5 PAN imagery. In Geoscience and Remote Sensing Symposium, 5: 3158-3160. [35] Walter, V (2004). Object-based classification of remote sensing data for change detection. ISPRS Journal of Photogrammetry and Remote Sensing 58(3–4), 225–238. [36] Yan G, Mas J.F, Maathuis B. H. P, Xiangmin Z and Dijk P. M. V. (2006). Comparison of pixel‐based and object‐oriented image classification approaches—a case studyin a coal fire area, Wuda, Inner Mongolia, China. International Journal of Remote Sensing, 27: 4039-4055. [37] Yuan, D. and Elvidge, C. (1998). NALC land cover change detection pilot study: Washington D.C. area experiments. Remote Sensing of Environment, 66, 166–178. | ||
|
آمار تعداد مشاهده مقاله: 523 تعداد دریافت فایل اصل مقاله: 417 |
||