ارزیابی روش‌های طبقه‌بندی شئ‌گرا و پیکسل مبنا در جداسازی سازندهای زمین‌شناسی با استفاده از تصاویر لندست 8 و بهره‌گیری از منطق بولین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد سنجش‌ازدور و سیستم اطلاعات جغرافیایی، گروه جغرافیا، پردیس علوم انسانی و اجتماعی، دانشگاه یزد، یزد، ایران.

2 دانشجوی دکتری سنجش‌ازدور، مرکز مطالعات سنجش‌ازدور و GIS، دانشگاه شهید بهشتی، تهران، ایران.

3 استادیار، گروه جغرافیا، بخش برنامه‌ریزی محیطی، پردیس علوم انسانی و اجتماعی، دانشگاه یزد، یزد، ایران.

4 دانشجوی دکتری مدیریت مناطق خشک و بیابانی، گروه مدیریت مناطق خشک و بیابانی، دانشکده منابع طبیعی و کویرشناسی، دانشگاه یزد، یزد، ایران.

چکیده

تهیه نقشه­‌های سنگ شناسی به کمک داده­‌های میدانی و دورکاوی به دلیل تنوع ساختاری زمین و مشکلاتی مانند دشواری دسترسی به بعضی مناطق، همیشه با خطا همراه بوده است. اما در دهه­‌های گذشته استفاده از تصاویر ماهواره‌­ای کمک شایانی در افزایش دقت و سرعت تهیه نقشه‌­های زمین‌شناسی داشته است. هدف از پژوهش حاضر، بررسی قابلیت استفاده از تصاویر ماهواره لندست-8 و روش‌های طبقه‌بندی پیکسل مبنا و ‌شئ‌گرا در تهیه نقشه سازندهای زمین‌شناسی بخشی از رشته کوه شیرکوه استان یزد می‌باشد. این منطقه جزء سلسله کوه‌­های پراکنده ایران مرکزی با اقلیم خشک و حداقل پوشش گیاهی است. در آغاز برای شناسایی سازندها با استفاده از پردازش‌­های: MNF, PCA و FCC بارزسازی انجام شد. سپس با بهره­‌گیری از خوارزمیک‌های (الگوریتم) شئ‌گرا (BAYES، SVM، KNN، DECISION TREE و RANDOM FOREST)، شبکه عصبی (ART MAP، RBF، MLP و SOM) و پیکسل مبنا (حداکثر احتمال، حداقل فاصله، ماهالانوبیس و SAM) ، طبقه‌­بندی شدند و مقدار خطای هرکدام از روش‌­ها با استفاده از منطق بولین و ضریب کاپا محاسبه شد. طبقه‌بندی حداکثر احتمال با ضریب کاپا 75% در دسته پیکسل مبنا، طبقه‌بندی آرتمپ فازی در روش شبکه عصبی با ضریب کاپا 72% و طبقه‌بندی بیز در روش شئ‌گرا  با ضریب کاپا 82% بهترین نتایج را در بین دیگر روش­‌های بررسی شده نشان­ دادند. این نتایج کارآمدی روش‌­های نامبرده شده را در شناسایی سازندهای زمین‌شناسی به اثبات می‌رساند. روش‌ SAM از روش‌های پیکسل مبنا، روش SOM از روش‌های شبکه عصبی و روش RF از روش‌های شئ‌گرا به‌ترتیب 49­%، 64­% و 61­% کمترین میزان دقت‌ نتایج را در هر دسته نشان دادند.

کلیدواژه‌ها


  1. Aboelkhair, H., Abdelhalim, A., Hamimi, Z., & Al-Gabali, M. (2020). Reliability of using ASTER data in lithologic mapping and alteration mineral detection of the basement complex of West Berenice, Southeastern Desert, Egypt. Arabian Journal of Geosciences13(7), 1-20.
  2. Abou Elmagd, K., Emam, A., & Ali-Bik, M. W. (2013). Chemostratigraphy, petrography and remote sensing characterization of the Middle Miocene-Holocene sediments of Ras Banas peninsula, Red Sea Coast, Egypt. Carpathian Journal of Earth and Environmental Sciences8(3), 27-42.
  3. Achour, S., Chikr Elmezouar, M., Taleb, N., Kpalma, K., & Ronsin, J. (2020). A PCA-PD fusion method for change detection in remote sensing multi temporal images. Geocarto International, 1-18.
  4. Aronoff, S. (1982). Classification accuracy: a user approach. Photogrammetric Engineering and Remote Sensing, 48(8), 1299-1307.
  5. Ali-Bik, M. W., Hassan, S. M., Abou El Maaty, M. A., Abd El Rahim, S. H., Abayazeed, S. D., & Wahab, W. A. (2018). The late Neoproterozoic Pan-African low-grade metamorphic ophiolitic and island-arc assemblages at Gebel Zabara area, Central Eastern Desert, Egypt: Petrogenesis and remote sensing-Based geologic mapping. African Earth Sciences144, 17-40.
  6. Ali-Bik, M. W., Taman, Z., Kalioubi, B., & Abdel Wahab, W. (2012). Serpentinite- hosted talc–magnesite deposits of Wadi Barramiya area, Eastern desert Egypt: characteristics, petrogenesis and evolution. African Earth Sciences, 64, 77–89.
  7. Ali-Bik, M. W., Abd El Rahim, S. H., Wahab, W. A., Abayazeed, S. D., & Hassan, S. M. (2017). Geochemical constraints on the oldest arc rocks of the Arabian-Nubian Shield: The late Mesoproterozoic to late Neoproterozoic (?) Sa'al volcano-sedimentary complex, Sinai, Egypt. Lithos284, 310-326.
  8. Aliabad, F. A., Shojaei, S., Zare, M., & Ekhtesasi, M. (2019). Assessment of the fuzzy ARTMAP neural network method performance in geological mapping using satellite images and Boolean logic. Environmental Science and Technology, 16(7), 3829-3838.
  9. Baatz, M. (1999). Object-oriented and multi-scale image analysis in semantic networks. In Proc. the 2nd International Symposium on Operationalization of Remote Sensing, Enschede, ITC, Aug. 1999.
  10. Basukala, A. K., Oldenburg, C., Schellberg, J., Sultanov, M., & Dubovyk, O. (2017). Towards improved land use mapping of irrigated croplands: Performance assessment of different image classification algorithms and approaches. European Journal of Remote Sensing50(1), 187-201.
  11. Bonn, F., & Rochon, G. (1996). Précis de Télédétection (Vol. 2), Applications Thématiques. Edition Marquis, Presses de l'Université du Québec,(AUPELF, Sainte-Foy).
  12. Bonn, F., & Rochon, G. (1992). Précis de Télédétection (Vol. 1), Applications Thématiques. Presses de l'Université du Québec,(AUPELF, Sainte-Foy).
  13. Breiman, L., & Cutler, A. (2017). Avalaibe online at: random forests. Retrieved September, 2021, from http://www.stat.Berkeley.edu/breiman /RandomForests /cc_home. htm.
  14. Caloz, R., & Collet, C. (2001). Traitements numériques d’images en télédétection. De La Physique Expérimentale Aux Sciences Et Systèmes De L’information Géographique, 185.
  15. Chen, M., Su, W., Li, L., Zhang, C., Yue, A., & Li, H. (2009). Comparison of pixel-based and object-oriented knowledge-based classification methods using SPOT5 imagery. WSEAS Transactions on Information Science and Applications3(6), 477-489.
  16. Chorowicz, J., & Deroin, J. P. (2004). La teledetection et la cartographie geomorphologique et geologique. Editions scientifiques GB Contemporary Publishing International. Teledatection, 4(2), 211–213.
  17. Costache, R., Bao Pham, Q., Corodescu-Roșca, E., Cîmpianu, C., Hong, H., Thi Thuy Linh, N., ... & Thai Pham, B. (2020). Using GIS, remote sensing, and machine learning to highlight the correlation between the land-use/land-cover changes and flash-flood potential. Remote Sensing12(9), 1422.
  18. Daniela, R., Ermanno, M., Antonio, P., Pasquale, R., & Marco, V. (2020). Assessment of Tuff sea cliff stability integrating geological surveys and remote sensing. case history from Ventotene island (Southern Italy). Remote Sensing12(12), 2006.
  19. Dannenberg, M., Wang, X., Yan, D., & Smith, W. (2020). Phenological characteristics of global ecosystems based on optical, fluorescence, and microwave remote sensing. Remote Sensing12(4), 671.
  20. DeFries, R. S., & Chan, J. C. W. (2000). Multiple criteria for evaluating machine learning algorithms for land cover classification from satellite data. Remote Sensing of Environment74(3), 503-515.
  21. Deroin, J. P. (2019). An overview on 40 years of remote sensing geology based on Arab examples. The Geology of the Arab World---An Overview, 427-453.
  22. Dhara, M., Sengar, V. K., Chattoraj, S. L., & Bhattacharjee, S. (2017). Mapping of alteration zones in mineral rich belt of South-East Rajasthan using remote sensing techniques. Environmental, Chemical, Ecological, Geological and Geophysical Engineering11(2), 154-158.
  23. Duro, D. C., Franklin, S. E., & 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 environment118, 259-272.
  24. Ellison, R. A., McMillan, A. A., & Lott, G. K. (2002). Ground characterization of the urban environment: a guide to best practice. British Geological Survey Internal Report.
  25. Ennih, N., & Liégeois, J. P. (2001). The Moroccan Anti-Atlas: The West African craton passive margin with limited Pan-African activity. Implications for the northern limit of the craton. Precambrian Research112(3-4), 289-302.
  26. Gabr, S. S., Hassan, S. M., & Sadek, M. F. (2015). Prospecting for new gold-bearing alteration zones at El-Hoteib area, South Eastern Desert, Egypt, using remote sensing data analysis. Ore Geology Reviews71, 1-13.
  27. Gad, S., & Kusky, T. (2007). ASTER spectral ratioing for lithological mapping in the Arabian–Nubian shield, the Neoproterozoic Wadi Kid area, Sinai, Egypt. Gondwana research11(3), 326-335.
  28. Girard, M. C., & Girard, C. M. (1999). Traitement des données de télédétection. Dunod, Paris.
  29. Girija, R., & Mayappan, S. (2019). Mapping of mineral resources and lithological units: A review of remote sensing techniques. Image and Data Fusion10(2), 79-106.
  30. Green, A. A., Berman, M., Switzer, P., & Craig, M. D. (1988). A transformation for ordering multispectral data in terms of image quality with implications for noise removal. IEEE Transactions on geoscience and Remote Sensing26(1), 65-74.
  31. Hamimi, Z., Hagag, W., Kamh, S., & El-Araby, A. (2020). Application of remote-sensing techniques in geological and structural mapping of Atalla Shear Zone and Environs, Central Eastern Desert, Egypt. Arabian Journal of Geosciences13, 414.
  32. Hassan, S. M., & Sadek, M. F. (2017). Geological mapping and spectral based classification of basement rocks using remote sensing data analysis: The Korbiai-Gerf nappe complex, South Eastern Desert, Egypt. African Earth Sciences134, 404-418.
  33. Haut, J. M., Alcolea, A., Paoletti, M. E., Plaza, J., Resano, J., & Plaza, A. (2020). Gpu-friendly neural networks for remote sensing scene classification. IEEE Geoscience and Remote Sensing Letters, 19, 1-5.
  34. He, J., Harris, J. R., Sawada, M., & Behnia, P. (2015). A comparison of classification algorithms using Landsat-7 and Landsat-8 data for mapping lithology in Canada’s Arctic. International Journal of Remote Sensing36(8), 2252-2276.
  35. Huang, C., Davis, L. S., & Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing23(4), 725-749.
  36. Huang, L., & Ni, L. (2008). Object-oriented classification of high-resolution satellite image for better accuracy. In Proceedings of the 8th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, 211-218.
  37. Kadavi, P. R., & Lee, C. W. (2018). Land cover classification analysis of volcanic island in Aleutian Arc using an artificial neural network (ANN) and a support vector machine (SVM) from Landsat imagery. Geosciences22(4), 653-665.
  38. Kettles, I. M., Rencz, A. N., & Bauke, S. D. (2000). Integrating Landsat, geologic, and airborne gamma ray data as an aid to surficial geology mapping and mineral exploration in the Manitouwadge area, Ontario. Photogrammetric Engineering and Remote Sensing66(4), 437-445.
  39. Kumar, R., Nandy, S., Agarwal, R., & Kushwaha, S. P. S. (2014). Forest cover dynamics analysis and prediction modeling using logistic regression model. Ecological Indicators45, 444-455.
  40. Lennon, R. (2002). Remote sensing digital image analysis: An introduction. United States: Esa/Esrin.
  41. Li, M., Ma, L., Blaschke, T., Cheng, L., & Tiede, D. (2016). A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments. Applied Earth Observation and Geoinformation49, 87-98.
  42. Liu, F., Wu, X., Sun, H., & Guo, Y. (2007). Alteration information extraction by applying synthesis processing techniques to Landsat ETM+ data: case study of Zhaoyuan Gold Mines, Shandong Province, China. China University of Geosciences18(1), 72-76.
  43. Liu, W., Yang, M., Xie, M., Guo, Z., Li, E., Zhang, L., Pei, T., & Wang, D. (2019). Accurate building extraction from fused DSM and UAV images using a chain fully convolutional neural network. Remote Sensing11(24), 2912.
  44. Mansourmoghaddam, M., Rousta, I., Zamani, M.S., Mokhtari, M.H., Karimi, M. & Alavipanah, S.K. (2021). Study and prediction of land surface temperature changes of Yazd city: Assessing the proximity and changes of land cover. RS and GIS for Natural Resources, 12(4) 1-27 (in Farsi).
  45. Mansourmoghaddam, M., Ghafarian Malamiri, H. R., Arabi Aliabad, F., Fallah Tafti, M., Haghani, M., & Shojaei, S. (2022). The separation of the unpaved roads and prioritization of paving these roads using UAV images. Air, Soil and Water Research15, 1-10.
  46. McHugh, M. L. (2012). Interrater reliability: the kappa statistic. Biochemia Medica22(3), 276-282.
  47. Nemmour-Zekiri, D., & Oulebsir, F. (2020). Application of remote sensing techniques in lithologic mapping of Djanet Region, Eastern Hoggar Shield, Algeria. Arabian Journal of Geosciences13(14), 1-10.
  48. Oruc, M., Marangoz, A. M., & Buyuksalih, G. (2004). Comparison of pixel-based and object-oriented classification approaches using Landsat-7 ETM spectral bands. International Archives Photogrammetry Remote Sensing Spatial Information Science35, 1118-22.
  49. Osama, A., Hagag, A., El-Dahshan, E. S. A., & Ismail, M. A. (2020). Remote sensing image scene classification using CNN-MLP with data augmentation. Optik221, 165356.
  50. Palash, M., Mamun, M. A., & Hossain, M. A. (2021). PCA-based feature reduction for hyperspectral remote sensing image classification. IETE Technical Review38(4), 377-396.
  51. Pradhan, R., Ghose, M. K., & Jeyaram, A. (2010). Land cover classification of remotely sensed satellite data using bayesian and hybrid classifier. Computer Applications7(11), 1-4.
  52. Prado, P. F., & Duarte, I. C. S. (2020). An overview and recent advances in fuzzy ARTMAP classifier usage for mapping purposes using remotely sensed data. Environmental Informatics Letters3(2), 86-97.
  53. Rajendran, S., Al-Khirbash, S., Pracejus, B., Nasir, S., Al-Abri, A. H., Kusky, T. M., & Ghulam, A. (2012). ASTER detection of chromite bearing mineralized zones in Semail Ophiolite Massifs of the northern Oman Mountains: Exploration strategy. Ore Geology Reviews44, 121-135.
  54. Richards, J. A. (1999). Remote sensing digital image analysis, Springer-Verlag, Berlin, pp. 240.
  55. Rounds, E. M. (1980). A combined nonparametric approach to feature selection and binary decision tree design. Pattern Recognition12(5), 313-317.
  56. Rudrapal, D., & Subhedar, M. (2015). Land cover classification using support vector machine. International Journal of Engineering Research & Technology4(09), 584-588.
  57. Sabins, J.R., Freeman, W.H., Co, S.F. (1987). Remote sensing: principles and interpretation. Geocarto International, 2, 251–251.
  58. Sadek, M. F., Ali-Bik, M. W., & Hassan, S. M. (2015). Late Neoproterozoic basement rocks of Kadabora-Suwayqat area, Central Eastern Desert, Egypt: geochemical and remote sensing characterization. Arabian Journal of Geosciences8(12), 10459-10479.
  59. Shang, S., He, K. N., Wang, Z. B., Yang, T., Liu, M., & Li, X. (2020). Sea clutter suppression method of HFSWR based on RBF neural network model optimized by improved GWO algorithm. Computational Intelligence and Neuroscience2020, 1-10.
  60. Shokouh Saljoughi, B., Hezarkhani, A., & Farahbakhsh, E. (2018). A comparison between knowledge-driven fuzzy and data-driven artificial neural network approaches for prospecting porphyry Cu mineralization; a case study of Shahr-e-Babak area, Kerman Province, SE Iran. Mining and Environment9(4), 917-940.
  61. Smith, A., & Ellison, R. A. (1999). Applied geological maps for planning and development: a review of examples from England and Wales, 1983 to 1996. Engineering Geology and Hydrogeology32(Supplement), 1-44.
  62. Tang, Y. (2013). Object-oriented change detection with multi-feature in urban high-resolution remote sensing imagery. Wuhan University, Wuhan, Papers, 1-162.
  63. Tehrany, M. S., Pradhan, B., & Jebuv, M. N. (2014). A comparative assessment between object and pixel-based classification approaches for land use/land cover mapping using SPOT 5 imagery. Geocarto International29(4), 351-369.
  64. Thompson, A., Hine, P. D., Poole, J. S., & Grieg, J. R. (1998). Environmental geology in land use planning. Report by Symonds Travers Morgan for the Department of the Environment, Transport and the Regions, UK.
  65. Tso, B., Mather, P.M. (2009). Classification methods for remotely sensed data (2nd ed.). Taylor and Francis Pub, America.
  66. Whiteside, T. G., Boggs, G. S., & Maier, S. W. (2011). Comparing object-based and pixel-based classifications for mapping savannas. Applied Earth Observation and Geoinformation13(6), 884-893.
  67. Xing, E., Jordan, M., Russell, S. J., & Ng, A. (2002). Distance metric learning with application to clustering with side-information. Advances in neural information processing systems15, 521-528.
  68. Yang, M. D., Huang, K. H., & Tsai, H. P. (2020). Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification. Remote Sensing12(14), 2327.
  69. Yu, C., Wang, L., Zhao, J., Hao, L., & Shen, Y. (2020). Remote sensing image classification based on RBF neural network based on fuzzy C-means clustering algorithm. Intelligent & Fuzzy Systems38(4), 3567-3574.
  70. Yusuf, F. R., Santoso, K. B., Ningam, M. U. L., Kamal, M., & Wicaksono, P. (2018, June). Evaluation of atmospheric correction models and Landsat surface reflectance product in Daerah Istimewa Yogyakarta, Indonesia. In IOP Conference Series: Earth and Environmental Science, 169(1), 012004.
  71. Zamri, N. E., Alway, A., Mansor, A., Mohd Kasihmuddin, M. S., & Sathasivam, S. (2020). Modified imperialistic competitive algorithm in hopfield neural network for boolean three satisfiability logic mining. Pertanika Journal of Science & Technology28(3), 983-1008.
  72. Zhang, J., Lu, C., Wang, J., Yue, X. G., Lim, S. J., Al-Makhadmeh, Z., & Tolba, A. (2020). Training convolutional neural networks with multi-size images and triplet loss for remote sensing scene classification. Sensors20(4), 1188.
  73. Zhang, Z., Zuo, R., & Xiong, Y. (2016). A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China. Science China Earth Sciences59(3), 556-572.