خوشه‌بندی نواحی مستعد کانه‌زایی آهن در محدوده اسفوردی مبتنی بر روش هیبریدی رهیافت دانش و داده مبنا

نوع مقاله : علمی-پژوهشی

نویسندگان

1 کارشناسی ارشد، دانشکدگان فنی، دانشکده مهندسی معدن، دانشگاه تهران، تهران

2 استادیار، دانشکدگان فنی، دانشکده مهندسی معدن، دانشگاه تهران، تهران

3 دکترا، دانشکده مهندسی معدن، نفت و ژئوفیزیک، دانشگاه صنعتی شاهرود، شاهرود

چکیده

در این پژوهش، یک رویکرد هیبریدی برای خوشه‌بندی نواحی مستعد کانه‌زایی مگنتیت-آپاتیت در محدوده برگه 1:100000 اسفوردی به کار گرفته شده است که تعداد بهینه خوشه‌ها به کمک یک روش داده محور و مدل فرکتال مقدار- مساحت (C-A) به دست آمده‌ است. بدین منظور، با توجه به ویژگی‌های متالوژنیکی ذخایر هدف در محدوده مورد مطالعه، 9 لایه شاهد که شامل نشانگرهای زمین‌شناسی، ژئوشیمیایی، ژئوفیزیکی و دورسنجی است، از مجموعه داده‌های مکانی استخراج و تولید شده‌اند. از منحنی پیش‌بینی- مساحت (P-A)، به عنوان یک روش داده محور برای تعیین وزن و اهمیت هر لایه استفاده شده ‌است. تکنیک همپوشانی شاخص جهت ادغام 9 لایه وزن‌دار شده، به کار گرفته شده ‌است. در الگوریتم‌های خوشه‌بندی، تعداد خوشه‌ها تاثیر قابل توجهی بر نتیجه مدلسازی پتانسیل معدنی دارد. برای تعیین تعداد صحیح خوشه‌ها، تعداد کلاس‌های نقشه نهایی تولید شده به کمک مدل فرکتالی مقدار- مساحت شناسایی و در ادامه از آن برای اجرای الگوریتم‌های خوشه‌بندی بدون نظارت استفاده شده ‌است. با فرض پنج خوشه (به عنوان تعداد بهینه خوشه‌ها)، سه الگوریتم خوشه‌بندی که شامل k-means، فازی c-means و نقشه خود سازمانده (SOM) است، برای شناسایی مناطق امیدبخش کانه‌زایی هدف به کار گرفته شده‌ است. در بین سه الگوریتم اجرا شده، الگوریتم k-means، بیشترین بازدهی را در شناسایی ذخایر شناخته شده آهن در محدوده مورد مطالعه داشته ‌است؛ به طوری که زون پتانسیل معرفی شده با 8 درصد مساحت محدوده، حدود 65% رخدادهای معدنی را شناسایی کرده است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Clustering of Areas Prone to Iron Mineralization in Esfordi Range based on a Hybrid Method of Knowledge- and Data-Driven Approaches

نویسندگان [English]

  • S.A. Agha Seyyed Mirzabozorg 1
  • M. Abedi 2
  • F. Ahmadi 3
1 M.Sc Student, School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran
2 Assistant Professor, School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran
3 Ph.D, Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Shahrood, Iran
چکیده [English]

In this study, a hybrid approach is established for clustering the most favorable regions  in association with magnetite-apatite mineralization at the Esfordi district in the central Iran. An optimum number of clusters is derived from a data-driven methodology through a concentration-area (C-A) fractal model of a synthesized geospatial data set. According to the metallogenic characteristics of the sought deposits, nine evidential layers deriving from geological, geochemical, geophysical, and remote sensing data were extracted. Prediction-area curve (P-A) was used as a data-driven method to determine the weight and importance of those evidences; then an index overlay method integrated them into a single propsectivity map. The number of clusters significantly affects the mineral potential modeling results in clustering algorithms. To determine an optimum number of clusters, the C-A fractal curve of the overlaid map indicated the correct population within this district, and then used as the optimal number to run the unsupervised clustering algorithms. Assuming five clusters, three clustering algorithms, including K-means, fuzzy C-means, and self-organizing map (SOM), were used to identify and localize iron-bearing favourable areas. The K-means algorithm had the highest accuracy in identifying those potential areas, by which 8% of the whole area could predict 65% of known deposits in the main favorable region.

کلیدواژه‌ها [English]

  • Clustering
  • Esfordi
  • Hybrid methods
  • Magnetite-apatite deposits
  • Mineral potential mapping
  1. Xiong, Y., Zuo, R., and Carranza, E. J. M. (2018). “Mapping mineral prospectivity through big data analytics and a deep learning algorithm”. Ore Geology Reviews, 102: 811-817.
  2. Cheng, Q. (2012). “Singularity theory and methods for mapping geochemical anomalies caused by buried sources and for predicting undiscovered mineral deposits in covered areas”. Journal of Geochemical Exploration, 122: 55-70.
  3. Torppa, J., Nykänen, V., and Molnár, F. (2019). “Unsupervised clustering and empirical fuzzy memberships for mineral prospectivity modelling”. Ore Geology Reviews, 107: 58-71.
  4. Carranza, E. J. M. (2017). “Natural Resources Research Publications on Geochemical Anomaly and Mineral Potential Mapping, and Introduction to the Special Issue of Papers in These Fields”. Natural Resources Research, 26(4): 379-410.
  5. Li, T., Zuo, R., Xiong, Y., and Peng, Y. (2021). “Random-Drop Data Augmentation of Deep Convolutional Neural Network for Mineral Prospectivity Mapping”. Natural Resources Research, 30(1): 27-38.
  6. Sun, T., Li, H., Wu, K., Chen, F., Zhu, Z., and Hu, Z. (2020). “Data-driven predictive modelling of mineral prospectivity using machine learning and deep learning methods: A case study from Southern Jiangxi Province, China”. Minerals, 10(2): 102.
  7. Abedi, M., Norouzi, G. H., and Torabi, S. A. (2013). “Clustering of mineral prospectivity area as an unsupervised classification approach to explore copper deposit”. Arabian Journal of Geosciences, 6(10): 3601-3613.
  8. Rezapour, M. J., Abedi, M., Bahroudi, A., and Rahimi, H. (2020). “A clustering approach for mineral potential mapping: A deposit–scale porphyry copper exploration targeting”. Geopersia, 10(1): 149-163.
  9. Rahimi, H., Abedi, M., Bahroudi, A., Rezapour, M. J., Elyasi, G. R., and Aslani, S. (2021). “A hybrid-based clustering algorithm for targeting porphyry copper mineralization at Chahargonbad district in SE Iran”. International Journal of Mining and Geo-Engineering, 55(1): 17–26.
  10. Abedi, M., Norouzi, G.-H., and Bahroudi, A. (2012) “Support vector machine for multi-classification of mineral prospectivity areas”. Computers & Geosciences, 46: 272-283.
  11. بهرامی، ی.، حسنی، ح.، مقصودی، ع.؛ 1400؛ "استفاده از روش ترکیبی AHP-TOPSIS به منظور مدل‌سازی پتانسیل معدنی مس در ورقه یکصدهزار ابهر، شمال غرب ایران". فصلنامه پژوهش‌های دانش زمین، دوره 12، شماره 1، ص 57-41.
  12. Bahrami, Y., Hassani, H., and Maghsoudi, A. (2019). “BWM-ARAS: A new hybrid MCDM method for Cu prospectivity mapping in the Abhar area, NW Iran”. Spatial Statistics, 33: 100382.
  13. Bencharef, M. H., Eldosouky, A. M., Zamzam, S., and Boubaya, D. (2022). “Polymetallic mineralization prospectivity modelling using multi-geospatial data in logistic regression: The Diapiric Zone, Northeastern Algeria”. Geocarto International, 37(27): 1-36.
  14. Agterberg, F. P., and Bonham-Carter, G. F. (1999). “Logistic regression and weights of evidence modeling in mineral exploration”. In Proceedings of the 28th international symposium on applications of computer in the mineral industry (APCOM), Golden, Colorado, pp. 490.
  15. Singer, D. A., and Kouda, R. (1996). “Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan”. Mathematical Geology, 28(8): 1017-1023.
  16. Bonham-Carter, G. F. (1989). “Weights of evidence modeling: a new approach to mapping mineral potential”. Statistical Applications in the Earth Sciences, 171-183.
  17. Maepa, F., Smith, R. S., and Tessema, A. (2021). “Support vector machine and artificial neural network modelling of orogenic gold prospectivity mapping in the Swayze greenstone belt, Ontario, Canada”. Ore Geology Reviews, 130: 103968.
  18. Ford, A. (2020). “Practical implementation of random forest-based mineral potential mapping for porphyry Cu–Au mineralization in the Eastern Lachlan Orogen, NSW, Australia”. Natural Resources Research, 29(1): 267-283.
  19. Hariharan, S., Tirodkar, S., Porwal, A., Bhattacharya, A., and Joly, A. (2017). “Random Forest-Based Prospectivity Modelling of Greenfield Terrains Using Sparse Deposit Data: An Example from the Tanami Region, Western Australia”. Natural Resources Research, 26(4): 489-507.
  20. Zhang, S., Xiao, K., Carranza, E. J. M., and Yang, F. (2019). “Maximum entropy and random forest modeling of mineral potential: Analysis of gold prospectivity in the Hezuo–Meiwu district, west Qinling Orogen, China”. Natural Resources Research, 28(3): 645-664.
  21. Ghezelbash, R., Maghsoudi, A., and Carranza, E. J. M. (2019). “Mapping of single- and multi-element geochemical indicators based on catchment basin analysis: Application of fractal method and unsupervised clustering models”. Journal of Geochemical Exploration, 199: 90-104.
  22. Carranza, E. J. M., Mangaoang, J. C., and Hale, M. (1999). “Application of mineral exploration models and GIS to generate mineral potential maps as input for optimum land-use planning in the Philippines”. Natural Resources Research, 8(2): 165-173.
  23. Bonham-Carter, G. F. (1994). “Geographic information systems for geoscientists. Modelling with GIS. Computer methods in the geosciences”. Elsevier. eBook ISBN: 9781483144948.
  24. Barak, S., Imamalipour, A., Abedi, M., Bahroudi, A., and Khalifani, F. M. (2021). “Comprehensive modeling of mineral potential mapping by integration of multiset geosciences data”. Geochemistry, 81(4):125824.
  25. Riahi, S., Bahroudi, A., Abedi, M., Aslani, S., and Lentz, D. R. (2022). “Evidential data integration to produce porphyry Cu prospectivity map, using a combination of knowledge and data‐driven methods”. Geophysical Prospecting, 70(2): 421-437.
  26. Barak, S., Abedi, M., and Bahroudi, A. (2020). “A knowledge-guided fuzzy inference approach for integrating geophysics, geochemistry, and geology data in a deposit-scale porphyry copper targeting, Saveh, Iran”. Bollettino di Geofisica Teorica ed Applicata, 61(2): 159-176.
  27. Riahi, S., Bahroudi, A., Abedi, M., and Aslani, S. (2022). “Hybrid outranking of geospatial data: Multi attributive ideal-real comparative analysis and combined compromise solution”. Geochemistry, 82(3): 125898.
  28. Carranza, E. J. M. (2011). “Geocomputation of mineral exploration targets”. Computers & Geosciences, 37(12): 1907-1916.
  29. Ghezelbash, R., Maghsoudi, A., Shamekhi, M., Pradhan, B., and Daviran, M. (2022). “Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity”. Neural Computing and Applications, 35: 719-733.
  30. Bigdeli, A., Maghsoudi, A., and Ghezelbash, R. (2022). “Application of self-organizing map (SOM) and K-means clustering algorithms for portraying geochemical anomaly patterns in Moalleman district, NE Iran”. Journal of Geochemical Exploration, 233: 106923.
  31. Rahimi, H., Abeedi, M., Yousefi, M., Bahroudi, A., and Elyasi, G. (2021). “Supervised mineral exploration targeting and the challenges with the selection of deposit and non-deposit sites thereof”. Applied Geochemistry, 128: 104940.
  32. Cohn, R., and Holm, E. (2021). “Unsupervised machine learning via transfer learning and k-means clustering to classify materials image data”. Integrating Materials and Manufacturing Innovation, 10(2): 231-244.
  33. Nabatian, G., Rastad, F., Honarmadn, M., and Ghaderi, M. (2015). “Iron and Fe--Mn mineralisation in Iran: implications for Tethyan metallogeny”. Australian Journal of Earth Sciences, 62(2): 211-241.
  34. Daliran, F. (2002). “Kiruna-type iron oxide-apatite ores and “apatitites” of the Bafq district, Iran, with an emphasis on the REE geochemistry of their apatites”. In: Porter, T. M. (Ed.), Hydrothermal Iron Oxide Copper Gold and Related Deposits: A Global Perspective, PGC Publishing, Adelaide, 2: 303-320.
  35. افضلی، س.، نظافتی، ن.، قادری، م.، قلمقاش، ج.، قاسمی، م.، کریمی باوندپور، ع.؛ 1393؛ "سنگ‌زایی و کانه‌زایی در کانسار اکسید آهن آپاتیت‌دار گزستان، خاور بافق، ایران مرکزی". فصلنامه علوم زمین، دوره 24، شماره 93، ص 84-77.
  36. بومری، م.؛ 1391؛ "بررسی کانی‌های خاکی کمیاب در کانسار مگنتیت-آپاتیت اسفوردی، ناحیه بافق". فصلنامه علوم زمین، دوره 22، شماره 85، ص 82-71.
  37. سپهری‌راد، ر.، علیرضایی، س.، عظیم‌زاده، ا.؛ 1397؛ "دگرسانی گرمابی در کانسار مگنیت-آپاتیت گزستان و مقایسه آن با دیگر کانسارهای آهن ناحیه بافق، ایران مرکزی". فصلنامه علوم زمین، دوره 27، شماره 108، ص 268-257.
  38. Daliran, F., Stosch, H.-G., Williams, P., Jamali, H., and Dorri, M. B. (2010). “Early Cambrian iron oxide-apatite-REE (U) deposits of the Bafq district, east-central Iran”. Exploring for Iron oxide copper--gold deposits: Canada and Global analogues. Geol Assoc Canada, Short Course Notes, 20: 143-155.
  39. نبی‌لو، م.، آرین، م.، افضل، پیمان.، ادیب، ا.، مهرنیا، ا.، 1397؛ "ارتباط کانه‌ازیی عنصر آهن با ساختارهای خطی پی‌سنگ به کمک مدل‌های فرکتالی چندگانه در منطقه بافق، ایران مرکزی". فصلنامه علوم زمین، شماره 108، ص 181-190.
  40. Nabilou, M., Afzal, P., Arian, M., Adib, A., Kheyrollahi, H., Foudazi, M., and Ansarirad, P. (2021). “The relationship between Fe mineralization and the magnetic basement structures using multifractal modeling in the Esfordi and Behabad Areas (BMD), central Iran”. Acta Geologica Sinica-English Edition.
  41. Daliran, F., Stosch, H. G., and Williams, P. (2007). “Multistage metasomatism and mineralization at hydrothermal Fe oxide-REE-apatite deposits and “apatitites” of the Bafq District, Central-East Iran”. In Digging Deeper, Proceedings of the 9th Biennial SGA Meeting Dublin, 1501-1504.
  42. Foerster, H., and Jafarzadeh, A. (1994). “The Bafq mining district in central Iran; a highly mineralized Infracambrian volcanic field”. Economic Geology, 89(8): 1697-1721.
  43. Shamseddin Meigooni, M., Lotfi, M., Afzal, P., and  Nezafati, N. (2021). “Detection of rare earth element anomalies in Esfordi phosphate deposit of Central Iran, using geostatistical-fractal simulation”. Geopersia, 11(1): 115-130.
  44. Mokhtari, M. A. A., Zadeh, G. H., and Emami, M. H. (2013). “Genesis of iron-apatite ores in Posht-e-Badam Block (Central Iran) using REE geochemistry”. Journal of Earth System Science, 122(3): 795-807.
  45. Torab, F. M. (2008). “Geochemistry and metallogeny of magnetite apatite deposits of the Bafq mining district, Central Iran”. Univ.-Bibliothek, pp. 131. ISBN: 3940394289.
  46. Yousefi, M., and Nykänen, V. (2016). “Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mapping”. Journal of Geochemical Exploration, 164: 94-106.
  47. Yousefi, M., and Carranza, E. J. M. (2017). “The efficiency of logistic function and prediction-area plot in prospectivity analysis of mineral deposits”. In Conference: Mineral ProspectivityAt: BRGM, Orleans, France.
  48. احمدی، ف.، آقاجانی، ح.، عابدی، م.؛ 1400؛ "تهیه نقشه پتانسیل معدنی با استفاده از تصاویر ماهواره‌ای سنتینل 2، لندست 8 و استر برای کانسار آهن در برگه 1:100000 اسفوردی". نشریه مهندسی منابع معدنی، دوره هفتم، شماره 2، ص 23-1.
  49. Ahmadi, F., Aghajani, H., and Abedi, M. (2021). “Geochemical potential mapping of iron-oxide targets by Prediction-Area plot and Concentration-Number fractal model in Esfordi, Iran”. International Journal of Mining and Geo-Engineering, 55(2): 171-181.
  50. Zuo, R. (2018). “Selection of an elemental association related to mineralization using spatial analysis”. Journal of Geochemical Exploration, 184: 150-157.
  51. Karar, K., Gupta, A. K., Kumar, A., and Biswas, A. K. (2006). “Characterization and identification of the sources of chromium, zinc, lead, cadmium, nickel, manganese and iron in PM10 particulates at the two sites of Kolkata, India”. Environmental Monitoring and Assessment, 120(1): 347-360.
  52. Reimann, C., Filzmoser, P., and Garrett, R. G. (2002). “Factor analysis applied to regional geochemical data: problems and possibilities”. Applied Geochemistry, 17(3): 185-206.
  53. Zumlot, A. B. T. (2012). “Multivariate statistical approach to geochemical methods in water quality factor identification; application to the shallow aquifer system of the Yarmouk Basin of north Jordan”. Research Journal of Environmental and Earth Sciences, 4(7): 756-768.
  54. Ammar, F. H., Chkir, N., Zouari, K., Hamelin, B., Deschamps, P., and Aigoun, A. (2014). “Hydro-geochemical processes in the Complexe Terminal aquifer of southern Tunisia: An integrated investigation based on geochemical and multivariate statistical methods”. Journal of African Earth Sciences, 100: 81-95.
  55. Nazarpour, A., Omran, N. R., and Paydar, G. R. (2015). “Application of multifractal models to identify geochemical anomalies in Zarshuran Au deposit, NW Iran”. Arabian Journal of Geosciences, 8(2):  877-889.
  56. Clark, D. A. (2014). “Magnetic effects of hydrothermal alteration in porphyry copper and iron-oxide copper--gold systems: A review”. Tectonophysics, 624: 46-65.
  57. Testa, F. J., Villanueva, C., Cooke, D. R., and Zhang, L. (2018). “Lithological and hydrothermal alteration mapping of epithermal, porphyry and tourmaline breccia districts in the Argentine Andes using ASTER imagery”. Remote Sensing, 10(2): 203.
  58. Nabilou, M., Arian, M., Afzal, P., Adib, A., and Mehrnia, A. K. (2018). “Determination of relationship between basement faults and alteration zones in Bafq-Esfordi region, central Iran”. Episodes Journal of International Geoscience, 41(3): 143-159.
  59. Cheng, Q., Agterberg, F. P., and Ballantyne, S. B. (1994). “The separation of geochemical anomalies from background by fractal methods”. Journal of Geochemical Exploration, 51(2): 109-130.
  60. Yousefi, M., and Carranza, E. J. M. (2015). “Prediction--area (P-A) plot and C-A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling”. Computers & Geosciences, 79: 69-81.
  61. Yousefi, M., and Carranza, E. J. M. (2016). “Data-driven index overlay and Boolean logic mineral prospectivity modeling in greenfields exploration”. Natural Resources Research, 25 (1): 3-18.
  62. Agterberg, F. P., and Bonham-Carter, G. F. (2005). “Measuring the performance of mineral-potential maps”. Natural Resources Research, 14(1): 1-17.
  63. Oskooi, B., and Abedi, M. (2015). “An airborne magnetometry study across Zagros collision zone along Ahvaz–Isfahan route in Iran”. Journal of Applied Geophysics, 123: 112-122.
  64. Abedi, M. and Oskooi, B. (2015). “A combined magnetometry and gravity study across Zagros orogeny in Iran”. Tectonophysics, 664: 164-175.