Maden Potansiyeli Tahmin Yöntemlerine Genel Bir Bakış

Abstract

Maden bulunabilirlik analizleri, maden aramalarını buluş şansı en yüksek sahalara yönlendirerek başarı oranını artırır ve maliyetleri düşürür. Geleneksel analizlerin öznelliği, 1960'lardan itibaren istatistiksel yöntemlerin kullanımıyla aşılmıştır. 1980'lerde Coğrafi Bilgi Sistemleri (CBS) teknolojisinin gelişimi, 2000'lerde makine öğrenimi ve veri bilimi yenilikleri, süreci daha nesnel ve etkili hâle getirmiştir. Bu analizler, bilgi odaklı ve veri odaklı olmak üzere iki ana yöntemle gerçekleştirilir. Bilgi odaklı sistemler, uzman görüşlerini taklit ederek yatak modeli veya mineral sistem yaklaşımlarına dayanır. Kanıt ağırlıkları yöntemi, bu sistemlerin en yaygın kullanılanıdır. CBS ile yer bilimi verileri birleştirilerek pozitif ve negatif ağırlıklar hesaplanır. Bayes teoremi kullanılarak olasılıklar güncellenir. ÇÖKA (Çok Ölçütlü Karar Verme Analizi), Bulanık Mantık gibi yöntemler de bilgi odaklı yaklaşımlar arasında yer alır. Veri odaklı sistemler, belirli bir model veya hipotez olmadan doğrudan verilerden öğrenir. İstatistiksel yöntemlerin yanı sıra, makine öğrenimi algoritmaları (destek vektör makineleri, yapay sinir ağları, karar ağaçları) karmaşık veri setlerindeki örüntüleri belirlemede güçlüdür. Bu yöntemler, arama süreçlerini daha sistematik ve nesnel tahmine dayalı hâle getirir. Ancak, başarıları veri kalitesine ve seçilen modellerin etkinliğine bağlıdır. Bu nedenle, doğru verilerin toplanması ve analiz süreçlerinin optimize edilmesi büyük önem taşır.

Keywords

• Maden Bulunabilirlik Analizi
• Bilgi Odaklı Yöntemler
• Veri Odaklı Yaklaşımlar
• Kanıt Ağırlıkları
• Makine Öğrenimi
• Coğrafi Bilgi Sistemleri (CBS)

A Review of Mineral Potential Estimation Methods

Abstract

Mining prospectivity analyses enhance success rates and reduce costs by directing exploration efforts toward areas with the highest discovery potential. The subjectivity of traditional analysis has been addressed since the 1960s through the use of statistical techniques. The development of geographic information systems (GIS) technology in the 1980s and advancements in machine learning and data science in the 2000s have made the process more objective and effective. These analyses are conducted using two main approaches: knowledge-driven and data-driven methods. Knowledge-driven systems mimic expert reasoning and rely on deposit models or mineral system approaches. The weight-of-evidence method is the most commonly used among these systems. GIS is used to integrate geoscientific data, to calculate positive and negative weights, and to update probabilities using Bayes' theorem. Other knowledge-driven approaches include analytic hierarchy process (AHP) and fuzzy logic. Data-driven systems learn directly from data without relying on predefined models or hypotheses. In addition to statistical methods (e.g., logistic regression analysis), machine learning algorithms—such as support vector machines, artificial neural networks, and decision trees—are highly effective in identifying patterns within complex datasets. These methods make exploration processes more systematic and predictive. However, their success depends on data quality and the effectiveness of the selected models. Therefore, collecting accurate data and optimizing analytical processes have great importance.

Keywords

• Mineral prospectivity analysis
• knowledge-driven approaches
• data-driven approaches
• weights of evidence
• machine learning
• geographic information systems (GIS)

References

1. Abedi, M., Norouzi, G-H. ve Bahroudi, A. (2012). Support vector machine for multi-classification of mineral prospectivity areas. Computers & Geosciences, 46, 272-283.
2. Agterberg, F.P. (1971). A probability index for detecting favourable geological environments. Canadian Institute of Mining and Metallurgy, 10, 82-91.
3. Agterberg, F. P. (1973). Probabilistic Models to Evaluate Regional Mineral Potential. In: Proc. Symposium on Mathematical Methods in the Geosciences, Přibram. 3-38.
4. Agterberg, F.P. (1974). Automatic contouring of geological maps to detect target areas for mineral exploration. Math. Geol., 6, 373–395.
5. Bonham-Carter, G.F., Agterberg, F.P. ve Wright, D.F. (1989). Weights of evidence modelling: a new approach to mapping mineral potential. Agterberg, F.P., Bonham-Carter, G.F. (Eds.), Statistical Applications in the Earth Sciences: Geological Survey Canada Paper 89-9, pp. 171–183.
6. Agterberg F.P. ve Cheng, Q.M. (2002). Conditional independence test for weights-of-evidence modelling. Nat Resour Res 11,249–255.
7. An, P., Moon, W. M. ve Rencz, A. N. (1991). Application of Dempster-Shafer theory of evidence to mineral potential mapping. Computers & Geosciences, 17(7), 889–896.
8. Bliss, J.D., ed. (1992). Developments in deposit modelling. U.S. Geological Survey Bulletin 2004, 168 s.

9. Bonham-Carter, G. F. (1994). Geographic Information Systems for Geoscientists: Modelling with GIS. Pergamon Press, 398s.
10. Bonham-Carter, G.F., Agterberg, F.P., ve Wright, D.F. (1989). Weights of evidence modelling: a new approach to mapping mineral potential, in Statistical applications in the earth sciences: Geol. Survey Canada Paper 89-9, p. 171-183.
11. Brown, W., Gedeon, T., Groves, D ve Barnes, R. (2000). Artificial Neural Networks: A New Method for Mineral Prospectivity Mapping. Australian Journal of Earth Sciences, 47. 757-770.
12. Carranza, E. J. M. (2008). Geochemical anomaly and mineral prospectivity mapping in GIS. (Handbook of exploration and environmental geochemistry, Vol. 11). Elsevier.
13. Carranza, E.J.M. (2009a). Chapter 7: Knowledge-Driven Modelling of Mineral Prospectivity. Emmanuel John M.(ed.), Geochemical Anomaly and Mineral Prospectivity Mapping in GIS, Elsevier Science B.V., 11, 189-247.
14. Carranza, E.J.M. (2009b). Chapter 8: Data-Driven Modelling of Mineral Prospectivity. Emmanuel John M.(ed.), Geochemical Anomaly and Mineral Prospectivity Mapping in GIS, Elsevier Science B.V., 11, 249-310.
15. Carranza, E.J.M. (2021). Mineral Prospectivity Analysis. Daya Sagar, B., Cheng, Q., McKinley, J., Agterberg, F. (eds) Encyclopaedia of Mathematical Geosciences. Encyclopaedia of Earth Sciences Series. Springer, Cham. 1-6.
16. Carranza, E.J.M., Hale, M. (2001). Geologically constrained fuzzy mapping of gold mineralization potential, Baguio district, Philippines. Natural Resources Research: 10, 125–136.
17. Carranza, E.J.M. ve Laborte, A.G. (2015). Random Forest predictive modelling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Comp. & Geosciences, 74, 60-70.
18. Carranza, E.J.M., Van Ruitenbeek, F.J.A., Hecker, C., van der Meijde, M. ve van der Meer, F.D. (2008). Knowledge-guided data-driven evidential belief modelling of mineral prospectivity in Cabo de Gata, SE Spain. Int. J. Appl. Earth Observ. Geoinform. 10 (3), 374–387.
19. Cheng, Q.ve Agterberg, F. P. (1999). Fuzzy Weights of Evidence Method and Its Application in Mineral Potential Mapping. Natural Resources Research 8, 27–35
20. Cox, D.P., Barton, P.B. ve Singer, D.A. (ed.). (1986). Mineral Deposit Models: U.S. Geological Survey Bulletin, 1693, 379s.
21. Drew, L. J. ve Menzie, W. D. (1993). Is there is metric for mineral deposit occurrence probabilities: Nonrenewable Resources, 2,92–105
22. Duda, R.O., Hart, P.E., Nilsson, N.J. ve Sutherland, G.L. (1978). Semantic network representations in rulebased interference systems. Waterman, D.A., Hayes-Roth, F. (Eds.), Pattern-Directed Inference Systems. Academic Press, 203–221.
23. Ferri, C., Flach, P.A., Hernandez-Orallo, J. (2003) Improving the AUC of probabilistic estimation trees. Proceedings of the 14th European Conference on Machine Learning, 121–132.
24. Harris, D.P. (1965). An application of multivariate statistical analysis to mineral exploration. Unpublished Ph.D. Dissertation, Pennsylvania State University, 261s.
25. Harris, D.P. (1969). Alaska's base and precious metals resources: a probabilistic regional appraisal. Quarterly of the Colorado School of Mines 64, 295–327.
26. Harris, D.P. ve Pan, G.C. (1999). Mineral favorability mapping: a comparison of artificial neural networks, logistic regression and discriminate analysis. Natural Resources Research 8, 93–109.
27. Harris, J., Grunsky, E., Behnia, P. ve Corrigan, D. (2015). Data- and Knowledge driven mineral prospectivity maps for Canada’s North. Ore Geology Reviews, 71, 788- 803.
28. Hronsky, J.M.A. ve Groves, D.I. (2008). Science of targeting: definition, strategies, targeting and performance measurement. Australian Journal of Earth Sciences 55, 3–12.
29. Hronsky, J. M. A. ve Kreuzer, O. P. (2019). Applying spatial prospectivity mapping to exploration targeting: Fundamental practical issues and suggested solutions for the future. Ore Geology Reviews, 107, 647–653.
30. Knox-Robinson, C.M. ve Wyborn, L.A.I. (1997). Towards a holistic exploration strategy: using geographic information systems as tool to enhance exploration. Australian Journal of Earth Sciences 44, 453–463.
31. Kreuzer, O.P., Etheridge, M.A., Guj, P., McMahon, M.E. ve Holden, D.J. (2008). Linking mineral deposit models to quantitative risk analysis and decision-making in exploration. Economic Geology 103, 829–850.
32. McCuaig, T.C., Beresford, S. ve Hronsky, J. (2010). Translating the mineral systems approach into an effective exploration targeting system. Ore Geology Reviews 38, 128–138.
33. McCuaig, T. ve Hronsky, J. (2000). The current status and future of the interface between the exploration industry and economic geology research. Reviews in Economic Geology. 13. 553-559.
34. McCuaig, T. C. ve Hronsky, J. M. A. 2005, The Mineral Systems Concept: Key to Exploration Targeting: Applied Earth Science IMM Transactions section B 18(2):153-175
35. McCuaig, T.C. ve Hronsky J.M.A. (2014). The mineral system concept: The key to exploration targeting. Society of Economic Geologists Special Publication 18, p. 153-175.
36. Mosier, D.L ve Page, N.J. (1988). Descriptive and grade-tonnage models of volcanogenic manganese deposits in ocean environments—A modification: U.S. Geological Survey Bulletin, 1811, 28 s.
37. Mosier, D.L, Berger., V.I. ve Singer, D. A. (2009). Volcanogenic Massive Sulfide Deposits of the World— Database and Grade and Tonnage Models: USGS, Open-File Report 2009-1034.
38. Özkan, Y. Z. (2004). Maden Arama Projelerinin Tasarımı ve Değerlendirilmesi. JMO Yayınları, No.82.
39. Özkan, Y. Z. (2023). Maden arama projelerinin optimizasyonu. Mayeb Basın Yayın İnsan Kaynakları Ltd. Şti.
40. Özkan, Y. Z. (2024). Maden Kaynak Belirleme Sondaj Programlarının Optimizasyonu. Jeoloji Mühendisliği Dergisi, 48, 203-228.
41. Pan, G. C., ve Harris, D. P. (2000). Information synthesis for mineral exploration. New York: Oxford University Press Inc. p. 460.
42. Pirajno, F. (2009). Hydrothermal Processes and Mineral Systems. Springer.
43. Porwal, A., Carranza, E.J.M. ve Hale, M. (2003). Artificial neural networks for mineral potential mapping: a case study from Aravalli province, western India. Natural Resources Research 12, 155–177.
44. Porwal, A., Carranza, E.J.M. ve Hale, M. (2004). A hybrid neuro-fuzzy model for mineral potential mapping. Mathematical Geology 36, 803–826.
45. Porwal, A., Carranza, E. J. M.ve Hale, M. (2003). A hybrid neuro-fuzzy model for mineral potential mapping. Mathematical Geology, 35(4), 403–424.
46. Porwal, A. ve Carranza, E.J.M. (2015). Introduction to the special issue: GIS-based mineral potential modelling and geological data analyses for mineral exploration. Ore Geol. Rev. 71, 477–483.
47. Porwal, A., Carranza, E.J.M. ve Hale, M. (2004). A Hybrid Neuro-Fuzzy Model for Mineral Potential Mapping. Mathematical Geology, 36(7), 803-826.
48. Porwal, A., Carranza, E.J.M. ve Hale, M. A. (2006). Hybrid Fuzzy Weights-of-Evidence Model for Mineral Potential Mapping. Nat Resour Res 15, 1–14).
49. Porwal, A.ve Hale, M. (2000). Extended weights of evidence modelling for predictive mapping of base metal potential: A case study in Aravalli province, western India. Natural Resources Research, 9(1), 59-76.
50. Porwal, of evidence and logistic regression modelling of magmatic nickel sulfide prospectivity in the Yilgarn Craton, Western Australia. Ore Geology Reviews 38, 184–196.
51. Porwal, A.K. ve Kreuzer, O. P. (2010). Introduction to the Special Issue: Mineral prospectivity analysis and quantitative resource estimation: Ore Geology Reviews, 38, 121-127.
52. Saaty, T. (1980). The Analytic Hierarchy Process. McGraw-Hill International Book Company.
53. Sinclair, A.J. ve Woodsworth, G.L. (1970). Multiple regression as a method of estimating exploration potential in an area near Terrace, B.C. Economic Geology 65, 998–1003.
54. Singer, D.A. (1972). Multivariate statistical analysis of the unit regional value of mineral resources. Unpublished Ph.D. Dissertation, Pennsylvania State University, 211 s.
55. Singer, D.A., Berger, V.I. ve Moring, B.C. (2009). Sediment-hosted zinc-lead deposits of the world- database and grade and tonnage models. U.S. Geological Survey, Open-file Report 2009–1252
56. Singer, D.A. ve Kouda, R. (1999). A comparison of the weights of evidence method and probabilistic neural networks. Natural Resources Research 8, 287–298.
57. Sun, T., Li, H., Wu, K., Chen, F., Zhu, Z. ve 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 2020, 10, 102.
58. Wyborn, L. A. I., Heinrich, C. A. ve Jaques, A. L. (1994). Australian Proterozoic mineral systems: Essential ingredients and mappable criteria. P.C. Hallenstein (Ed.), Australian Mining Looks North—the Challenges and Choices, Australian Institute of Mining and Metallurgy Publication Series, 5 (1994), pp. 109-115.
59. Yang, N., Zhang, Z., Yang, J. ve Hong, Z. (2022). Applications of data augmentation in mineral prospectivity prediction based on convolutional neural networks. Comput. Geosci., 161
60. Zhang, N. ve Zhou, K. (2015). Mineral prospectivity mapping with weights of evidence and fuzzy logic methods. Journal of Intelligent & Fuzzy Systems, 29, 6, 2639-2651.
61. Zuo, R. (2020). Geodata Science-Based Mineral Prospectivity Mapping: A Review. Nat Resour Res 29, 3415– 3424.
62. Zuo, R. ve Carranza, E.l J.M. (2011). Support vector machine: A tool for mapping mineral prospectivity. Comput. Geosci., 37,1967-1975.
63. Zuo, R., Xiong, Y., Wang, J. ve Carranza, E.J.M. (2019). Deep learning and its application in geochemical mapping. Earth-Sci. Rev., 192, 1–14