Economic and Environmental Geology (자원환경지질)

The Korean Society of Economic and Environmental Geology (대한자원환경지질학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Titanium bearing Myeonsan Formation in the Joseon Supergroup based on Spectral Analysis and Machine Learning Techniques

분광분석과 기계학습기법을 활용한 조선누층군 타이타늄 함유 면산층 탐지

  • Park, Chanhyeok (Department of Astronomy, Space Science, & Geology, Chungnam National University) ;
  • Yu, Jaehyung (Department of Geological Sciences, Chungnam National University) ;
  • Oh, Min-Kyu (Department of Astronomy, Space Science, & Geology, Chungnam National University) ;
  • Lee, Gilljae (Rare Metal Ore Research Center, Korea Institute of Geoscience and Mineral Resources) ;
  • Lee, Giyeon (Department of Geological Sciences, Chungnam National University)
  • 박찬혁 (충남대학교 우주.지질학과) ;
  • 유재형 (충남대학교 지질환경과학과) ;
  • 오민규 (충남대학교 우주.지질학과) ;
  • 이길재 (한국지질자원연구원 희소금속광상연구센터) ;
  • 이기연 (충남대학교 지질환경과학과)
  • Received : 2022.04.08
  • Accepted : 2022.04.26
  • Published : 2022.04.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study investigated spectroscopic exploration of Myeonsan formation, the titanium(Ti) ore hostrock, in Joseon supergroup based on machine learning technique. The mineral composition, Ti concentration, spectral characteristics of Myeonsan and non-Myeonsan formation of Joseon supergroup were analyzed. The Myeonsan formation contains relatively larger quantity of opaque minerals along with quartz and clay minerals. The PXRF analysis revealed that the Ti concentration of Myeosan formation is at least 10 times larger than the other formations with bi-modal distribution. The bi-modal concentration is caused by high Ti concentrated sandy layer and relatively lower Ti concentrated muddy layer. The spectral characteristics of Myeonsan formation is manifested by Fe oxides at near infrared and clay minerals at shortwave infrared bands. The Ti exploration is expected to be more effective on detection of hostrock rather than Ti ore because ilmenite does not have characteristic spectral features. The random-forest machine learning classification detected the Myeonsan fomation at 85% accuracy with overall accuracy of 97%, where spectral features of iron oxides and clay minerals played an important role. It indicates that spectral analysis can detect the Ti host rock effectively, and can contribute for UAV based remote sensing for Ti exploration.

본 연구는 조선누층군 내 타이타늄 광체의 모암이 되는 면산층 암석을 기계학습기법을 분광분석 결과에 적용하여 탐지하였다. 이를 위해 면산층과 타 층들의 구성 광물을 파악하고, 타이타늄 함량을 측정하였으며, 전자기파 반응 특성을 분석하였다. 면산층은 다른 층들에 비해 불투명 광물을 많이 함유하고, 석영 입자와 점토광물로 구성된다. X선 형광분석 결과, 면산층의 평균 타이타늄 함량은 타 층들에 비해 최소 10배 이상의 타이타늄 함량을 보이며 낮은 함량군과 높은 함량군의 다봉분포를 갖는다. 이는 면산층 내의 타이타늄이 함유되는 사질과 이질이 교호 반복되는데 사질 부분은 이질 부분보다 타이타늄의 함량이 상대적으로 높기 때문이다. 분광분석 결과, 면산층은 산화철의 흡광 특성이 근적외선 영역에서, 점토광물에 의한 흡광 특성이 단파적외선 영역에서 관찰되며, 풍화면의 경우 점토광물 특성이 보다 강해지는 경향을 보인다. 타이타늄 광화대의 탐지는 티탄철석 자체의 분광 특성이 특징적이지 않아 광체를 탐지의 대상으로 보기보다는 모암인 면산층을 탐지하는 것이 적절할 것으로 생각된다. 랜덤포레스트 기계학습 기법을 이용한 면산층의 탐지 정확도는 84%, 전체정확도 97%를 보였으며, 산화철의 분광 특성과 점토광물 분광 특성이 가장 중요한 역할을 하는 것으로 분석되었다. 이는 분광 특성이 타이타늄 모암인 면산층 암석을 효율적으로 탐지할 수 있음을 지시하고, 확대 적용 될경우 무인항공기반 타이타늄 광체 탐사에 적용할 수 있을 것으로 기대한다.

Keywords

Acknowledgement

본 논문을 심사해 주신 심사위원님들께 감사드린다. 이 논문은 충남대학교 혁신지원사업(2021-2022) 지원을 받아 작성되었다.

References

  1. Breiman, L. (2001) Random forests. Mach. Learn., v.45, p.5-32. https://doi.org/10.1023/A:1010933404324
  2. Calvin, W.M. and Pace, E.L. (2016) Mapping alteration in geothermal drill core using a field portable spectroradiometer. Geothermics, v.61, p.12-23. doi: https://doi.org/10.1016/j.geothermics.2016.01.005.
  3. Cheong, C.H., Lee, D.S., Um, S.H. and Chang, K.H. (1973) Investigation of Geological Classification of Korea. Ministry of Science and Technology, R-73-51, 68p (in Korean).
  4. Cho, E. and Hong, J. (2021) Cyclic patterns in the Lower Ordovician Dumugol Formation, Korea: Influence of compaction on sequence-stratigraphic interpretation in mixed carbonate-shale successions. Sedimentary Geology, v.420.
  5. Choi, D.K., Chough, S.K., Kwon, Y.K., Lee, S.-B., Woo, J., Kang, I., Lee, H.S., Lee, S.M., Sohn, J.W., Shinn, Y.J. and Lee, D.-J. (2004) Taebaek Group(Cambrian-Ordovician) in the Seokgaejae section, Taebaeksan Basin: a refined lower Paleozoic stratigraphy in Korea. Geosciences Journal, v.8, p.125-151. https://doi.org/10.1007/BF02910190
  6. Choi, S.J., Kim, C.H. and Lee, S.G. (2009) Comparison of the Heavy Metal Analysis in Soil Samples by Bench-Top ED-XRF and Field-Portable XRF. Analytical Science and Technology, v.22(4), p.293-301 (in Korean and English Abstract). https://doi.org/10.5806/AST.2009.22.4.293
  7. Chough, S.K. (2013) Geology and Sedimentology of the Korean Peninsula. Elsevier Insights, Elsevier, 363p.
  8. Chung, B., Yu, J., Wang, L., Kim, N.H., Lee, B.H., Koh, S. and Lee, S. (2020) Detection of Magnesite and Associated Gangue Minerals using Hyperspectral Remote Sensing-A Laboratory Approach. Remote Sensing, v.12, p.1325-1351. https://doi.org/10.3390/rs12081325
  9. Geological Investigation Corps of Taebaeksan Region (GICTR) (1962) Report on the Geology and Mineral Resources of the Taebaegsan Region. Geological Society of Korea, Seoul, 89p.
  10. Herrmann, W., Blake, M., Doyle, M., Huston, D., Kamprad, J., Merry, N. and Pontual, S. (2001). Short wavelength infrared (SWIR) spectral analysis of hydrothermal alteration zones associated with base metal sulfide deposits at Rosebery and Western Tharsis, Tasmania, and Highway-Reward, Queensland. Economic Geology, v.96(5), p.939-955. doi: https://doi.org/10.2113/gsecongeo.96.5.939.
  11. Hong, J., Lee, J.-H., Choh, S.-J. and Lee, D.-J. (2016) Cambrian Series 3 carbonate platform of Korea dominated by microbial-sponge reefs. Sedimentary Geology, v.341, p.58-69. https://doi.org/10.1016/j.sedgeo.2016.04.012
  12. Huynh, H. H., Yu, J., Wang, L., Kim, N. H., Lee, B. H., Koh, S. M., Cho, S. and Pham, T. H. (2021) Integrative 3D Geological Modeling Derived from SWIR Hyperspectral Imaging Techniques and UAV-Based 3D Model for Carbonate Rocks. Remote Sensing, v.13(15), p.3037. https://doi.org/10.3390/rs13153037
  13. Jeong, Y., Yu, J., Wang, L. and Lee, K. J. (2021) Bulk scanning method of a heavy metal concentration in tailings of a gold mine using SWIR hyperspectral imaging system. International Journal of Applied Earth Observation and Geoinformation, v.102, p.102382. https://doi.org/10.1016/j.jag.2021.102382
  14. Kim, B, Song, S.Y., Cho, S.O. and Nam, M.J. (2018) Status of Reserves and Development Technology of Rare Earth Metals in Korea. Journal of the Korean Society of Mineral and Energy Resources Engineers, v.55(1), p.67-82. doi:10.12972/ksmer.2018.55.1.067
  15. Kim, H., Yu, J., Wang, L., Jeong, Y. and Kim, J. (2020) Variations in spectral signals of heavy metal contamination in mine soils controlled by mineral assemblages. Remote Sensing, v.12(20), p.3273. https://doi.org/10.3390/rs12203273
  16. Kim, J.Y. (1991) Stratigraphy of the Myeonsan Formation in Samcheog-gun, Kangwon-do and Ponghwagun, Kyongsangbukdo. Journal of the Geological Society of Korea, v.27, p.225-245 (in Korean with English abstract).
  17. Kim, J.Y. and Cheong, C.H. (1987) The Precambrian-Cambrian boundary in the east of the Dongjeom fault, Gangweon-do, Korea. Journal of the Geological Society of Korea, v.23, p.145-158 (in Korean with English abstract).
  18. Koh S.M. (2015) Development of Advanced beneficiation Process for Rare Metal Minerals. Korea Institute of Geoscience and Mineral Resources
  19. Kokaly, R.F. and Clark, R.N. (1999) Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression. Remote Sensing of Environment, v.67(3), p.267-287. https://doi.org/10.1016/S0034-4257(98)00084-4
  20. Kwon, Y.K., Chough, S.K., Choi, D.K. and Lee, D.-J. (2006) Sequence stratigraphy of the Taebaek Group (Cambrian-Ordovician). mideast Korea. Sedimentary Geology, v.192, p.19-55. https://doi.org/10.1016/j.sedgeo.2006.03.024
  21. Lawrence, R.L., Wood, S.D. and Sheley, R.L. (2006) Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest). Remote Sensing of Environment, v.100(3), p.356-362. https://doi.org/10.1016/j.rse.2005.10.014
  22. Lee, J.-H., Cho, S.H., Jung, D.Y., Choh, S.-J. and Lee, D.-J. (2021a) Ribbon rocks revisited: the upper Cambrian (Furongian) Hwajeol Formation, Taebaek Group, Korea. Facies, v.67.
  23. Lee, J.-H., Hong, J., Woo, J.S., Oh, J.-R., Lee, D.-J. and Choh, S.-J. (2016) Reefs in the Early Paleozoic Taebaek Group, Korea: A review. Acta Geologica Sinica, v.90, p.352-367. https://doi.org/10.1111/1755-6724.12659
  24. Lee, J.-H., Oh, M.-K. and Choi, T. (2021b) Recognition of the "Great Unconformity" in the eastern Sino-Korean Block: Insights from the Taebaek Group, Korea. Precambrian Research, v.364, p.106363. https://doi.org/10.1016/j.precamres.2021.106363
  25. Liaw, A. and Wiener, M. (2002) Classification and regression by random Forest. R News, v.2(3), p.18-22.
  26. Lide, D. R., ed. (2005) CRC Handbook of Chemistry and Physics(86thed.). Boca Raton (FL): CRC Press.ISBN 0-8493-0486-5.
  27. Oh, M.-K. (2020) Sedimentology of the Hydrothermally Altered Myobong Formation (lower Cambrian), Taebaek, Korea. M.S. Thesis. Chungnam National University. p. 67.
  28. Parnell, J. Mark, D.F. Frei, R. Fallick, A.E. and Ellam, R.M. (2014) 40Ar/39Ar dating of exceptional concentration of metals by weathering of Precambrian rocks at the Precambrian-Cambrian boundary. Precambrian Research, v.246, p.54-63. doi: https://doi.org/10.1016/j.precamres.2014.02.012
  29. Rodriguez-Galiano, V.F., Ghimire, B., Rogan, J., Chica-Olmo, M. and Rigol-Sanchez, J.P. (2012) An assessment of theeffectiveness of a Random Forest classifier for land-cover classification. ISPRS J. Photogramm. Remote Sens., v.67, p.93-104. https://doi.org/10.1016/j.isprsjprs.2011.11.002
  30. Shi, T., Chen, Y., Liu, Y. and Wu, G. (2014) Visible and near-infrared reflectance spectroscopy-An alternative formonitoring soil contamination by heavy metals. J. Hazard. Mater., v.265, p.166-176. https://doi.org/10.1016/j.jhazmat.2013.11.059
  31. Shim, K., Yu, J., Wang, L., Lee, S., Koh, S.M. and Lee, B.H. (2021) Content Controlled Spectral Indices for Detection of Hydrothermal Alteration Minerals Based on Machine Learning and Lasso-Logistic Regression Analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, v.14, p.7435-7447. https://doi.org/10.1109/JSTARS.2021.3095926.
  32. Shin, H., Yu, J., Wang, L., Jeong, Y. and Kim, J. (2019) Spectral interference of heavy metal contamination on spectral signals of moisture content for heavy metal contaminated soils. IEEE Transactions on Geoscience and Remote Sensing, v.58(4), p.2266-2275. https://doi.org/10.1109/TGRS.2019.2946297.
  33. Woo, J., Shinn, Y.J., Kwon, Y.K. and Chough, S.K. (2006) The Jangsan and Myeonsan formations (Early Cambrian) of the Taebaek Group, mideast Korea: depositional processes and environments. Geosciences Journal, v.10, p.35-57. https://doi.org/10.1007/BF02910331
  34. Yoo, B.C. (2020) Occurrence and Chemical Composition of Ti-bearing Minerals from Samgwang Au-ag Deposit. Republic of Korea.Korean Journal of Mineralogy and Petrology, v.33(3), p.195-214. https://doi.org/10.22807/KJMP.2020.33.3.195
  35. Zadeh, M.H., Tangestani, M.H., Roldan, F.V. and Yusta, I. (2014) Spectral characteristics of minerals in alteration zones associated with porphyry copper deposits in the middle part of Kerman copper belt, SE Iran. Ore Geology Reviews, v.62, p.191-198. doi: https://doi.org/10.1016/j.oregeorev.2014.03.013.