Automatic lithological mapping from potential field data using machine learning: a case study from Mundiyawas-Khera Cu deposit, Rajasthan, India

Singh, Bhawesh Kumar; Gangumalla, Srinivasa Rao; Arasada, Rama Chandrudu; Kumar, Thinesh

doi:10.1007/s11600-023-01151-z

Artykuł - szczegóły

Tytuł artykułu

Automatic lithological mapping from potential field data using machine learning: a case study from Mundiyawas-Khera Cu deposit, Rajasthan, India

Autorzy

Singh Bhawesh Kumar , Gangumalla Srinivasa Rao , Arasada Rama Chandrudu , Kumar Thinesh

Wybrane pełne teksty z tego czasopisma

https://www.springer.com/journal/11600

Identyfikatory

DOI

10.1007/s11600-023-01151-z

Warianty tytułu

Języki publikacji

Abstrakty

Potential field data play a vital role in mineral resource mapping, especially in deriving the lithological information of poorly mapped terrains. The Mundiyawas-Khera area of the Alwar basin in Rajasthan, India, is known for Cu mineralization hosted within the felsic volcanic rocks. However, much of the area is covered with soil and needs detailed lithological mapping. In this study, different machine learning (ML) algorithms have been employed to integrate the digital elevation, drilling wells, gravity, and magnetic data, together with their derivatives, for obtaining accurate lithology information of the area. Initially, five different ML algorithms, random forest (RF), K-nearest neighbor, support vector machine, multi-layer perceptron (MLP), and gradient boosting (GB) were employed using 540 samples from six lithological units to obtain the refined lithologic map of the area. Subsequently, a stacking classifier was built, considering the best-performing ML models in the base learner. Comparison of evaluation matrices (precision, recall, and confusion matrix) of these ML algorithms suggests that RF, GB, and stack model (RF + GB + MLP with RF meta-classifier) provide the highest accuracy score (RF: 74.69%, GB: 74.69%, and stack: 75.31%) and class membership probabilities in predicting the lithology. Adding derivatives and analytic signal information to the input data improves the classification accuracy of ML models by ~ 5-8%. Overall the study results demonstrate that ensemble ML algorithms can aid in creating the first-pass lithology map of areas with limited outcrops, drilling, and geochemical data.

Słowa kluczowe

machine learning stacking gravity data magnetic data lithology classification

uczenie maszynowe układanie dane grawitacyjne dane magnetyczne

Wydawca

Instytut Geofizyki PAN
Springer

Czasopismo

Acta Geophysica

Rocznik

2024

Tom

Vol. 72, no. 2

Strony

777--792

Opis fizyczny

Bibliogr. 67 poz.

Twórcy

autor

Singh Bhawesh Kumar

Department of Applied Geophysics, IIT (ISM) Dhanbad, Jharkhand 826004, India

autor

Gangumalla Srinivasa Rao

gsrao@iitism.ac.in

Department of Applied Geophysics, IIT (ISM) Dhanbad, Jharkhand 826004, India

https://orcid.org/0000-0002-4119-5831

autor

Arasada Rama Chandrudu

Department of Applied Geophysics, IIT (ISM) Dhanbad, Jharkhand 826004, India

autor

Kumar Thinesh

CMPDIL, Coal India Limited, Ranchi 834 008, India

Bibliografia

1. Abedi M, Norouzi GH (2012) Integration of various geophysical data with geological and geochemical data to determine additional drilling for copper exploration. J Appl Geophys 83:35-45
2. Aitken ARA, Holden EJ, Dentith MC (2013) Semiautomated quantification of the influence of data richness on confidence in the geologic interpretation of aeromagnetic maps. Geophysics 78:J1-J13. https://doi.Org/10.1190/geo2012-0033.1
3. Anifowose F, Labadin J, Abdulraheem A (2015) Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines. Appl Soft Comput 26:483-496
4. Azam MS, Khan MS, Raza M (2015) Petrogenetic study of Mesoproterozoic volcanic rocks of North Delhi fold belt, NW Indian shield: implications for mantle conditions during Proterozoic. Chin j Geochem 34:93-114
5. Bhattacharya S, Carr TR, Pal M (2016) Comparison of supervised and unsupervised approaches for mudstone lithofacies classification: case studies from the Bakken and Mahantango-Marcellus Shale, USA. J Natl Gas Sci Eng 33:1119-1133
6. Blakely RJ (1995) Potential theory in gravity and magnetic applications. Cambridge University Press, Cambridge, p 437
7. Blaschke T (2010) Object based image analysis for remote sensing.
8. ISPRS J Photogramm Remote Sens 65:2-16
9. Breiman L (1996) Bagging predictors. Mach Learn 24:23-140
10. Breiman L (2001) Random forests. Mach Learn 45:5-32
11. Bressan TS, de Souza MK, Girelli TJ, Junior FC (2020) Evaluation of machine learning methods for lithology classification using geophysical data. Comput Geosci 139:104475
12. Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd International conference on knowledge discovery and data mining, pp 785-794
13. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21-27
14. Cracknell MJ, Reading AM (2014) Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput Geosci 63:22-33
15. Cracknell MJ, Reading AM, McNeill AW (2014) Mapping geology and volcanic-hosted massive sulfide alteration in the Hellyer-Mt Charter region, Tasmania, using Random Forests™ and SelfOrganising Maps. Aust J Earth Sci 61:287-304
16. Deb M (2014) Precambrian geodynamics and metallogeny of the Indian shield. Ore Geol Rev 57:1-28
17. Elbegue AA, Allek K, Zeghouane H (2022) Geological mapping using extreme gradient boosting and the deep neural networks: application to silet area, central Hoggar, Algeria. Acta Geophys 70:1581-1599
18. Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38:367-378
19. Fu G, Lü Q, Yan J, Farquharson CG, Qi G, Zhang K, Zhang Y, Wang H, Luo F (2021) 3D mineral prospectivity modeling based on machine learning: a case study of the Zhuxi tungsten deposit in northeastern Jiangxi Province, South China. Ore Geol Rev 13:104010
20. Hall B (2016) Facies classification using machine learning. Lead Edge 35:906-909
21. Haykin S (2009) Neural networks and learning machines, 3rd edn.
22. Prentice Hall, New York, p 938
23. Ho TK (1995) Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition, vol 1. IEEE, pp 278-282
24. Holden EJ, Fu SC, Kovesi P, Dentith M, Bourne B, Hope M (2011) Automatic identification of responses from porphyry intrusive systems within magnetic data using image analysis. Appl Geophys 74:255-262
25. Holden EJ, Wong JC, Kovesi P, Wedge D, Dentith M, Bagas L (2012) Identifying structural complexity in aeromagnetic data: an image analysis approach to greenfields gold exploration. Ore
26. Geol Rev 46:47-59. https://doi.org/10.1016/j.oregeorev.2011. 11.002
27. Jia R, Lv Y, Wang G, Carranza E, Chen Y, Wei C, Zhang Z (2021) A stacking methodology of machine learning for 3D geological modeling with geological-geophysical datasets, Laochang Sn camp, Gejiu (China). Comput Geosci 151:104754
28. Kaur P, Zeh A, Okrusch M, Chaudhri N, Gerdes A, Brätz H (2016) Separating regional metamorphic and metasomatic assemblages and events in the northern Khetri complex, NW India: evidence from mineralogy, whole-rock geochemistry and U-Pb monazite chronology. J Asian Earth Sci 129:117-141
29. Kaur P, Zeh A, Chaudhri N (2019) Archean crustal evolution of the Aravalli Banded Gneissic Complex, NW India: Constraints from zircon U-Pb ages, Lu-Hf isotope systematics, and whole-rock geochemistry of granitoids. Precambrian Res 327:81-102
30. Khan I, Rai DK, Sahoo PR (2013) A note on new find of thick copper and associated precious metal mineralisation from Alwar basin of North Delhi Fold Belt, Rajasthan. J Geol Soc India 82:495
31. Khan I, Sahoo PR, Rai DK (2014) Proterozoic felsic volcanics in Alwar Basin of North Delhi Fold Belt, Rajasthan: implication for copper mineralization. Curr Sci 106:27-28
32. Khan I, Chauhan A (2018) Final report on preliminary exploration for copper and associated precious metals in Mundiyawas block, Mundiyawas-Khera area, Alwar district, Rajasthan (stage: unfc G-3); Final Report 2016- 2017. Unpubld Geol Surv India
33. Khan I, Sahoo PR, Rai DK (2015) Geological set up of low grade copper-gold mineralization at Mundiyawas-Khera area, Alwar district, Rajasthan; In: Golani PR (ed) Recent developments in metallogeny and mineral exploration in Rajasthan, vol 101. Geol Soc India Spec Publ. pp 43-58
34. Khan I (2021) Metallogenetic significance and exploration strategies of copper-gold mineralization near Mundiyawas-Khera Area, Alwar Basin, Rajasthan, Western India. PhD Thesis Indian Institute of Technology (Indian School of Mines) Dhanbad India (Unpublished)
35. Knight J (2002) The Khetri copper belt, Rajasthan: iron-oxide coppergold terrane in the proterozoic of NW India. Hydrothermal Iron Oxide Copper Gold Relat Deposit Glob Perspect 2:321-341
36. Kotsiantis SB (2007) Supervised machine learning: a review of classification techniques. Informatica 31:249-268
37. Kuhn S, Cracknell MJ, Reading AM (2018) Lithologic mapping using random forests applied to geophysical and remote-sensing data: a demonstration study from the Eastern Goldfields of Australia. Geophysics 83:B183-B193
38. Kumar T, Seelam NK, Rao GS (2022) Lithology prediction from well log data using machine learning techniques: a case study from Talcher coalfield, Eastern India. J Appl Geophys 199:1-15
39. Lal RK, Ackermand D (1981) Phase-petrology and polyphase andalusite-sillimanite type regional metamorphism in pelitic schists of the area around Akhwali, Khetri Copper Belt, Rajasthan, India. Neues Jahrb Für Mineral Abhandlungen 141(2):161-185
40. Maria Navin JR, Pankaja R (2016) Performance analysis of text classification algorithms using confusion matrix. Int J Eng Tech Res 6:75-78
41. Masoumi F, Eslamkish T, Abkar AA, Honarmand M, Harris JR (2017) Integration of spectral, thermal, and textural features of ASTER data using random forests classification for lithological mapping. J Afr Earth Sci 129:445-457
42. McCormack MD (1991) Neural computing in geophysics. Lead Edge 10:11-15
43. Mehdi M, Kumar S, Pant NC (2015) Low grade metamorphism in the Lalsot-Bayana sub-basin of the North Delhi Fold Belt and its tectonic implication. J Geol Soc India 85:397-410
44. Mukhopadhyay S (2009) STM of Delhi Supergroup of rocks in Jod-hawas-Kushalgarh area, Alwar district, Rajasthan. Unpubld Geol Surv India Progress Report FS 2006-07
45. Nabighian MN (1984) Toward a three-dimensional automatic interpretation of potential field data via generalized Hilbert transforms; fundamental relations. Geophysics 49:780-786. https://doi.org/ 10.1190/1.1441706
46. Naha K, Mitra SK, Biswal TK (1987) Structural history of the rocks of the Delhi Group around Todgarh, Central Rajasthan. Indian J Geol 59:126-156
47. Nathan D, Aitken A, Holden EJ, Wong J (2020) Imaging sedimentary basins from high-resolution aeromagnetics and texture analysis. Comput Geosci 136:104396
48. Powar KB, Patwardhan AM (1984) Tectonic evolution and base-metal mineralisation in the Aravalli-Delhi belt, India. Precambrian Res 25:309-323
49. Pradhan B, Jena R, Talukdar D, Mohanty M, Sahu BK, Raul AK, Abdul Maulud KN (2022) A new method to evaluate gold mineralisation-potential mapping using deep learning and an explainable artificial intelligence (XAI) model. Remote Sens 14:4486
50. Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann, San Francisco
51. Rao GS, Arasada RC, Sahoo PR, Khan I (2019) Integrated geophysical investigations in the Mudiyawas-Khera block of the Alwar basin of North Delhi Fold Belt (NDBF): implications on copper and associated mineralisation. J Earth Syst Sci 128:1-13
52. Roest WR, Verhoef J, Pilkington M (1992) Magnetic interpretation using the 3-D analytic signal. Geophysics 57:116-125
53. Sarkar SC, Dasgupta S (1980) Geologic setting, genesis and transformation of sulfide deposits in the northern part of Khetri copper belt, Rajasthan, India—an outline. Miner Deposita 15:117-137
54. Serbouti I, Raji M, Hakdaoui M, El Kamel F, Pradhan B, Gite S, Alamri A, Maulud KNA, Dikshit A (2022) Improved lithological map of large complex semi-arid regions using spectral and textural datasets within google earth engine and fused machine learning multi-classifiers. Remote Sens 1414:5498
55. Singh SP (1988) Sedimentation patterns of the Proterozoic Delhi Supergroup, northeastern Rajasthan, India, and their tectonic implications. Sediment Geol 58:79-94
56. Smyth P (1999) Probabilistic model-based clustering of multivariate and sequential data. In: Proceedings of the seventh international workshop on AI and statistics. Morgan Kaufman, San Francisco, pp 299-304
57. Sun Z, Jiang B, Li X, Li J, Xiao K (2020) A data driven approach for lithology identification based on parameter-optimized ensemble learning. Energies 13:3903
58. Ting KM, Witten IH (1999) Issues in stacked generalization. J Artif Intell Res 10:271-289
59. Van der Baan M, Jutten C (2000) Neural networks in geophysical applications. Geophysics 65:1032-1047
60. Vapnik V (1995) The nature of statistical learning theory. Springer, New York, p 188
61. Wang K, Zhang L (2008) Predicting formation lithology from log data by using a neural network. Pet Sci 5:242-246
62. Waske B, Benediktsson JA, Árnason K, Sveinsson JR (2009) Mapping of hyperspectral AVIRIS data using machine-learning algorithms. Can J Remote Sens 35:S106-S116
63. Wijns C, Perez C, Kowalczyk P (2005) Theta map: edge detection in magnetic data. Geophysics 70:L39-L43
64. Wolpert DH (1992) Stacked generalization. Neural Netw 5:249-251
65. Xie Y, Zhu C, Zhou W, Li Z, Liu X, Tu M (2017) Evaluation of machine learning methods for formation lithology identification: a comparison of tuning processes and model performances. J Pet Sci Eng 160:182-193
66. Xu Y, Li Z, Xie Z, Cai H, Niu P, Liu H (2021) Mineral prospectivity mapping by deep learning method in Yawan-Daqiao area. Gansu Ore Geol Rev 13:104316
67. Yu L, Porwal A, Holden EJ, Dentith MC (2012) Towards automatic lithological classification from remote sensing data using support vector machines. Comput Geosci 45:229-239

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-acb6137f-c9f6-49f9-aa0f-d3617ba6ca84