بررسی رفتار ژئوشیمیایی عنصر مس به روش کا-میانگین و پیش‏بینی آن توسط شبکه عصبی مصنوعی در منطقه کیوی، استان اردبیل

نوع مقاله : علمی - پژوهشی

نویسندگان

1 اکتشاف معدن، دانشکده مهندسی معدن نفت و ژئوفیزیک، دانشگاه صنعتی شاهرود

2 استاد یار- دانشگاه مهندسی معدن- دانشگاه صنعتی شاهرود

3 استاد - عضو هیئت علمی دانشگاه صنعتی امیرکبیر

چکیده

این پژوهش بر روی برگه یک‏صدهزارم ژئوشیمیایی کیوی انجام شد که توسط سازمان زمین‏شناسی و اکتشافات معدنی ایران با استفاده از آنالیز شیمیایی نمونه های رسوبات آبراهه‏ای تهیه شده است. منطقه کیوی در استان اردبیل قرار دارد. این ناحیه شامل سه واحد سنگی رسوبی، آذرین و دگرگونی می‏باشد. قدیمی ترین واحد رسوبی موجود، سنگ‏های قبل از کرتاسه و جدیدترین آن، مربوط به کواترنر و عهد حاضر است. با توجه به استعداد کانی‏سازی فلزی، بالاخص عنصر مس در این منطقه، بررسی دقیق آن با اهمیت است. بر این اساس، یافتن اطلاعاتی در مورد ارتباط و رفتار عناصر طلا، نقره و مولیبدن نسبت به عنصر مس در این منطقه اهمیت می‏یابد؛ هدف از این بررسی، رفتارسنجی هاله‏های ژئوشیمیایی در منطقه می باشد. در پژوهش حاضر با هدف رفتارسنجی عناصر نام برده، از روش مشهور و مفید کا میانگین استفاده شد. این روش از روش‏های خوشه‏بندی است که بر کمینه کردن مجموع فواصل اقلیدسی هر یک از نمونه‏ها از مرکز دسته‏هایی که به آن تخصیص می‏یابد، استوار می‏باشد. در این پژوهش از تابع کیفیت خوشه‏بندی و میزان مطلوبیت نمونه در خوشه مورد نظر (S(i)) برای تشخیص تعداد خوشه بهینه استفاده شد، سپس با در نظرگرفتن مراکز خوشه ها و نتایج‏ حاصل، معادلاتی به منظور پیش‏بینی مقدار عنصر مس ارائه شد. ا پس از بررسی های رفتاری عناصر، آزمایش شبکه عصبی مصنوعی برای تخمین میزان مس با استفاده از روش‏های رگرسیون عمومی و پس انتشار خطا انجام شد. مقدار صحت (R) تخمین در داده ‏های آزمایشی در شبکه عصبی مصنوعی رگرسیون عمومی و پس انتشار خطا به ترتیب 0.77 و 0.74 گزارش شد. در انتها مشخص شدکه روش شبکه عصبی مصنوعی رگرسیون عمومی در تخمین بهینه عنصر مس در منطقه مورد مطالعه دارای ارجحیت است.

کلیدواژه‌ها

عنوان مقاله [English]

Geochemical Behavior Investigation Based on K-means and Artificial Neural Network Prediction for Copper, in Kivi region, Ardabil province, IRAN

نویسندگان [English]

  • Adel Shirazy 1
  • Mansour Ziaii 2
  • Ardeshir Hezarkhani 3
1 Mining exploration, Faculty of Mining Petroleum and Geophysics, Shahrood University of Technology
2 Associate Professor, Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Semnan, Iran.
3 Professor, Department of Mining & Metallurgical Engineering, Amirkabir University of Technology, Tehran, Iran.
چکیده [English]

Kivi region is located in Ardabil province of Iran. This research is on kivi geochemical sheet (on scale 1:100000) which is investigated by geological survey & mineral explorations of Iran (GSI) using stream sediment analyzes. This region consists of sedimentary, igneous and metamorphic rock units. The oldest existing sedimentary unit, the pre-Cretaceous rocks and the newest, is related to Quaternary and the present. Due to the ability of metal mineralization, especially the copper element in this region, it is important to study it carefully. Accordingly, finding information about the relation and behavior of the elements of gold, silver and molybdenum to the copper element in this region is important. The purpose of this study is to determine the behavior of geochemical halos in region. In this study with the aim of geochemical behavior investigating the mentioned elements K-means method was used. This method is based on clustering methods that minimize the total Euclidean intervals of each sample from the center of the groups to which it is assigned. In this research, the clustering quality function ( p(k) ) and the desirability of sample in the desired cluster ( S (i) ) were usedto determine the optimum numberof clusters. Then, taking into account clusters centers and results, equations were provided to predict the amount of copper with a special look at the method. After elemental behavioral studies, an artificial neural network test using general regression and backward propagation of errors was conducted to estimate the amount of copper. The accuracy value (R) of the estimation in the experimental data in the artificial neural network of general regression and backward propagation of errors was 0.77 and 0.74, respectively. Finally, it was determined that the general regression artificial neural network method has an advantage inThe optimal estimation of copper element in the studyarea.

کلیدواژه‌ها [English]

  • Kivi Region
  • Copper
  • Artificial Neural Network (ANN)
  • K-means Clustering
  • Geochemical Behavior Investigation

مراجع

  1. منابع

    1. Majdifar, S., Kamali, GH. (2014). Iron Grade Estimation Using ANFIS Algorithm at Tappeghermez Anomaly of Sangan Mine. Journal of Analytical and Numerical Methods in Mining Engineering (ANM). No 5. (in Persian)
    2. Abbas zadeh, S., Rahimi pour, GH., Najmodini, M. (2013). Recognition of Cu-Porphyry Mineralization Areas by Using One and multivariate integration methods on drainage geochemical data in Ghale Askar area, Kerman province. Journal of Analytical and Numerical Methods in Mining Engineering (ANM). No, 6. (in Persian)
    3. ShayesteFar, M., Rasa, I. (2005). Multivariate Data Analysis of Qanat Marvan Lead-Zinc Deposit., Kerman. Geosciences Scientific Quarterly Journal. No, 57. (in Persian)
    4. Malyszko, D., Wierzchon, S. T. (2007). Standard and Genetic K-means Clustering Techniques in Image Segmentation. In 6th International Conference on Computer Information Systems and Industrial Management Applicatins.
    5. Abolhassani, B., Salt, J. E. (2005). A Simplex Kmeans Algorithm for Radio-Port Placement in Cellular Networks. In Canadaian Conference on Electrical and Computer Engineering.
    6. Chen, T. W., Chien, S. Y. (2009). Bandwidth Adaptive Hardware Architecture of K-Means Clustering for Video Analysis. IEEE Transactions on VLSI Systems.
    7. Yang, J., Zhuang, Y., Wu, F. (2012). ESVCbased extraction and segmentation of texture features. Computers & Geosciences, Elsevier, 49, 238-247.
    8. Mora, J.L., Armas-Herrera, C.M., Guerra, J.A., Rodríguez-Rodríguez, A., Arbelo, C.D., (2012), Factors affecting vegetation and soil recovery in the Mediterranean woodland of the Canary Islands (Spain). Journal of Arid Environments, Elsevier, 87, 58-66.
    9. Meshkani, S. A., Mehrabi, B., Yaghubpur, A., Alghalandis, Y. F., (2011). The application of geochemical pattern recognition to regional prospecting: A case study of the Sanandaj–Sirjan metallogenic zone, Iran. Journal of Geochemical Exploration, Elsevier, 108, 183-195.
    10. Sfidari, E., Kadkhodaie-Ilkhchi, A., Najjari, S., (2012), Comparison of intelligent and statistical clustering approaches to predicting total organic carbon using intelligent systems. Journal of Petroleum Science and Engineering, Elsevier,63, 190-205.
    11. Wegner, T., Hussein, T., Hämeri, K., Vesala, T., Kulmala, M., Weber, S., (2012). Properties of aerosol signature size distributions in the urban environment as derived by cluster analysis. Atmospheric Environment, Elsevier, 61, 350-360.
    12. Moradzade, A., Dowlati Ardejani, F., Rooki, R., Rahimi, M., (2012). Estimation of permeability of South Pars gas field using general regression neural network. Journal of Erth and Space Phisycs, Volume 37, No 4, 51-65.
    13. Mohaghegh, S. and Ameri, S., 1995, Artificial Neural Network As A Valuable Tool For Petroleum Engineers, SPE29220, Proceedings, SPE, West Virginia.
    14. Balan, B., Mohaghegh, S., & Ameri, S. (1995). State-of-the-art in permeability determination from well log data: Part 1-A comparative study, model development. In SPE Eastern Regional Meeting. Society of Petroleum Engineers.
    15. Mohaghegh, S. (2000). Virtual-intelligence applications in petroleum engineering: Part 1—Artificial neural networks. Journal of Petroleum Technology, 52(09), 64-73.
    16. HIJANG, Z., & WILLIAMSON, M. A. (1994). Geological pattern recognition and modelling with a general regression neural network. Canadian Jl of Exploration Geophysics, 30(1), 60-68.
    17. Hasani, H., Shirazi, A., Shirazy, A., (2017), Estimation of copper values by artificial neural network in the sub-domain of Mashran, East of Iran, 2nd National Conference on Modern Science and Technology of Iran, Tehran, Association for the Development and Promotion of Basic Sciences and Techniques. (in Persian)
    18. Zhang, L., & Bai, G. (2002). Application of the artificial neural network to multivariate anomalyrecognition in geochemical exploration for hydrocarbons. Geochemistry: Exploration, Environment, Analysis, 2(1), 75-81.
    19. Lacassie, J. P., Del Solar, J. R., Roser, B., & Hervé, F. (2006). Visualization of volcanic rock geochemical data and classification with artificial neural networks. Mathematical Geology, 38(6), 697-710.
    20. Ho, T. L. (2009). 3-D inversion of borehole-to-surface electrical data using a back-propagation neural network. Journal of Applied Geophysics, 68(4), 489-499.
    21. Lalor, G. C., & Zhang, C. (2001). Multivariate outlier detection and remediation in geochemical databases. Science of the total environment, 281(1-3), 99-109.
    22. Pradhan, B., Lee, S., & Buchroithner, M. F. (2010). A GIS-based back-propagation neural network model and its cross-application and validation for landslide susceptibility analyses. Computers, Environment and Urban Systems, 34(3), 216-235.
    23. Geological Survey and Mineral Exploration of Iran (GSI), geology 1:100000 map, Kivi, Ardebil, Reports. Code: 5665
    24. Geological Survey and Mineral Exploration of Iran (GSI), Waterway map(1:100,000), kivi. Code: 5665
    25. Geological Survey and Mineral Exploration of Iran (GSI), Geochemical Studies Tracking Report on 1:100,000 sheet, kivi. Code: 5665
    26. Geological Survey and Mineral Exploration of Iran (GSI), Geology 1:100000 map, Kivi, Ardabil, Code 6356 .
    27. Myers, L., & Sirois, M. J. (2006). Spearman correlation coefficients, differences between. Wiley StatsRef: Statistics Reference Online.
    28. Jain, A. K. (2012). Data clustering: 50 years beyond K-Means, Pattern Recognition Letters, Elsevier, 31, 651-666.
    29. Saha, S., Bandy opadhyay, S. (2013). A generalized automatic clustering algorithm in a multi objective framework. Applied Soft Computing, Elsevier, 13, 89-108.
    30. Ghannadpour, S. S., Hezarkhani, A., & Farahbakhsh, E. (2013). An investigation of Pb geochemical behavior respect to those of Fe and Zn based on k-Means clustering method. Journal of Tethys, 1(4), 291-302.
    31. Schalkoff, R. J. (1997). Artificial neural networks (Vol. 1). New York: McGraw-Hill.
    32. Yegnanarayana, B. (2009). Artificial neural networks. PHI Learning Pvt. Ltd..
    33. Dayhoff, J. E., & DeLeo, J. M. (2001). Artificial neural networks. Cancer, 91(S8), 1615-1635.
    34. Abraham, A. (2005). Artificial neural networks. handbook of measuring system design.
    35. Demuth, H., & Beale, M. (1993). Neural Network Toolbox For Use with Matlab--User'S Guide Verion 3.0.
    36. Rolon, L. F. (2002). Developing intelligent synthetic logs: Application to Upper Devonian units in Pennsylvania.
    37. Specht, D. F. (1991). A general regression neural network. IEEE transactions on neural networks, 2(6), 568-576.
    38. Artun, E., Mohaghegh, S. D., Toro, J., Wilson, T., & Sanchez, A. (2005). Reservoir characterization using intelligent seismic inversion. In SPE Eastern Regional Meeting. Society of Petroleum Engineers.
    39. Demuth, H., & Beale, M. (2002). Neural Network Toolbox For Use with Matlab--User'S Guide Verion 4.0.
    40. Widrow, B., Glover, J. R., McCool, J. M., Kaunitz, J., Williams, C. S., Hearn, R. H., ... & Goodlin, R. C. (1975). Adaptive noise cancelling: Principles and applications. Proceedings of the IEEE, 63(12), 1692-1716.
    41. Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception (pp. 65-93).
    42. Buscema, M. (1998). Back propagation neural networks. Substance use & misuse, 33(2), 233-270.
    43. Goh, A. T. C. (1995). Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 9(3), 143-151.
    44. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.
    45. Hagan, M. T., & Menhaj, M. B. (1994). Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks, 5(6), 989-993.
    46. Chen, F. C. (1990). Back-propagation neural networks for nonlinear self-tuning adaptive control. IEEE Control systems magazine, 10(3), 44-48.
    47. Menard, J. J. (1995). Relationship between altered pyroxene diorite and the magnetite mineralization in the Chilean Iron Belt, with emphasis on the El Algarrobo iron deposits (Atacama region, Chile)., Mineral Deposita, Springer-Verlag, 30, 268-274.
    48. Leiluo, X., Xianwu, B., Ruizhong, H., Xingchun, Z. (2012). Relationships between porphyry Cu–Mo mineralization in the Jinshajiang– Red Rivermetallogenic belt and tectonic activity: Constraints from zircon U–Pb and molybdenite Re– Os geochronology., Ore Geology Reviews, Elsevier, 48, 460–473.
    49. Tarkian, M., Stribrny, B. (1999). Platinumgroup elements in porphyry copper deposits: a reconnaissance study.Mineralogy & Petrology,Springer-Verlag,65,161 183.
    50.  Talesh Hosseini, S., Asghari, O., & Ghavami Riabi, S. R. (2018). Spatial modelling of zonality elements based on compositional nature of geochemical data using geostatistical approach: a case study of Baghqloom area, Iran. Journal of Mining and Environment, 9(1), 153-167.
    51. Yaghini, M., Ghannad pour, F., Khadmatlu, S., (2008). Offering an clustering innovative method in data mining by using genetic algorithms to solve a real case study in the rail transportation industry, Iran Data Mining Conference. Amirkabir university. Tehran. ( in Persian)
    52.  Hezarkhani, A. Ghannadpour, S. S. (2015). Geochemical Behavior Investigation Based on K-Means Clustering: Basics, Concepts and Case Study. LAP LAMBERT Academic Publishing.
    53. Shina, H.W. and Sohnb, S.Y. (2004). Segmentation of Stock Trading Customers According to Potential Value,Expert Systems with Applications,27,27-33
    54. Shirazy, A., (2017). Modeling and delineation of copper anomalies using modern methods in Mesgaran cu deposit, East Iran. Msc Thesis. Birjand University of Technology, South Khorasan (in Persian).
    55. Mahvash Mohammadi, N., Hezarkhani, A. (2015). Estimation og grade gold in khooni deposit using the behavior of gold arsenic and antimony by clustering k-mean method. Journal of analytic and numerical methods in mining engineering 5(10):77-92
    56. Specht, D. F. (1996). Probabilistic neural networks and general regression neural networks. In Fuzzy logic and neural network handbook (pp. 301-344). McGraw-Hill, Inc..
    57. Gaborski, R. S. (1991). U.S. Patent No. 5,052,043. Washington, DC: U.S. Patent and Trademark Office.

نشریه مهندسی معدن
دوره 14، شماره 45
اسفند 1398
صفحه 96-112

فایل ها

سابقه مقاله

  • تاریخ دریافت: 02 تیر 1398
  • تاریخ بازنگری: 08 مهر 1398
  • تاریخ پذیرش: 10 اسفند 1398

هم رسانی

ارجاع به این مقاله

آمار