A Machine learning approach for the magnetic data interpretation of 2-D dipping dike

• Autorzy: Aimol Sh Bronson , Rao G. Srinivasa , Kumar Thinesh , Arasada Rama Chandrudu

Identyfikatory

DOI

10.1007/s11600-022-00937-x

• Języki publikacji: EN

Abstrakty

EN

2-D dipping dike model is often used in the magnetic anomaly interpretations of mineral exploration and regional geodynamic studies. However, the conventional interpretation techniques used for modeling the dike parameters are quite challenging and time-consuming. In this study, a fast and efficient inversion algorithm based on machine learning (ML) techniques such as K-Nearest Neighbors (KNN), Random Forest (RF), and XGBoost is developed to interpret the magnetic anomalies produced by the 2-D dike body. The model parameters estimated from these methods include the depth to the top of the dike (z), half-width (d), Amplitude coefficient (K), index angle (α), and origin (x0). Initially, ML models are trained with optimized hyper-parameters on simulated datasets, and their performance is evaluated using Mean absolute error (MAE), Root means squared error (RMSE), and Squared correlation (R2). The applicability of the ML algorithms was demonstrated on the synthetic data, including the effect of noise and nearby geological structures. The results obtained for synthetic data showed good agreement with the true model parameters. On the noise-free synthetic data, XGBoost better predicts the model parameters of dike than KNN and RF. In comparison, its performance decreases with increasing the percentage of noise and geological complexity. Further, the validity of the ML algorithms was also tested on the four field examples: (i) Mundiyawas-Khera Copper deposit, Alwar Basin, (ii) Pranhita–Godavari (P-G) basin, India, (iii) Pima Copper deposit of Arizona, USA, and (iv) Iron deposit, Western Gansu province China. The obtained results also agree well with the previous studies and drill-hole data.

Słowa kluczowe

EN

magnetic anomalies; machine learning; inversion; 2-D dipping dike

PL

anomalie magnetyczne; nauczanie maszynowe; inwersja

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2023
• Tom: Vol. 71, no. 2
• Strony: 681--696
• Opis fizyczny: Bibliogr. 69 poz.

Twórcy

autor

Aimol Sh Bronson

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

autor

Rao G. Srinivasa

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

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

autor

Kumar Thinesh

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

autor

Arasada Rama Chandrudu

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

Bibliografia

• 1. Abdelrahman EM, Essa KS (2015) A new method for depth and shape determinations from magnetic data. Pure Appl Geophys 172:439–460
• 2. Abdelrahman EM, El-Arby HM, El-Arby TM, Essa KS (2003) A least-squares minimization approach to depth determination from magnetic data. Pure Appl Geophys 160(7):1259–1271
• 3. Abdelrahman EM, Abo-Ezz ER, Soliman KS, El-Araby TM, Essa KS (2007) A least-squares window curves method for interpretation of magnetic anomalies caused by dipping dikes. Pure Appl Geophys 164:1027–1044
• 4. Al-Garni MA (2015) Interpretation of magnetic anomalies due to dipping dikes using neural network inversion. Arab J Geosci 8:8721–8729
• 5. Altman NS (1992) An introduction to kernel and nearest-neighbor non-parametric regression. Am Stat 46:175–185
• 6. Asfahani J, Tlas M (2004) Nonlinearly constrained optimization theory to interpret magnetic anomalies due to vertical faults and thin dikes. Pure Appl Geophys 161:203–219
• 7. Asfahani J, Tlas M (2007) A robust non-linear inversion for the interpretation of magnetic anomalies caused by faults, thin dikes and spheres like structure using stochastic algorithms. Pure Appl Geophys 164:2023–2042
• 8. Atchuta Rao D, Ram Babu HV, Venkata Raju DC (1985) Inversion of gravity and magnetic anomalies over some bodies of simple geometric shape. Pure Appl Geophys 123:239–249
• 9. Bastani M, Pedersen LB (2001) Automatic interpretation of magnetic dike parameters using the analytical signal technique. Geophysics 66:551–561
• 10. Beiki M, Pedersen LB (2012) Estimating magnetic dike parameters using a non-linear constrained inversion technique: an example from the Särna area, west central Sweden. Geophys Prospect 60:526–538
• 11. 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 Nat Gas Sci Eng 33:1119–1133
• 12. Biswas A (2018) Inversion of source parameters from magnetic anomalies for mineral/ore deposits exploration using global optimization technique and analysis of uncertainty. Nat Resour Res 27(1):77–107
• 13. Biswas A (2021) Rao K (2021) Interpretation of magnetic anomalies over 2D fault and sheet-type mineralized structures using very fast simulated annealing global optimization: an understanding of uncertainty and geological implications. Lithosphere 2021(Special 6):2964057
• 14. Biswas A, Parija MP, Kumar S (2017) Global non-linear optimization for the interpretation of source parameters from total gradient of gravity and magnetic anomalies caused by thin dyke. Ann Geophys 60:G0218–G0218
• 15. Breiman L (2001) Random forests. Mach Learn 45:5–32
• 16. 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
• 17. Chen T, Guestrin C (2016) XG-Boost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785–794
• 18. Chen J, Schiek-Stewart C, Lu L, Witte S, Eres Guardia K, Menapace F, Devarakota P, Sidahmed M (2020) Machine learning method to determine salt structures from gravity data. In SPE annual technical conference and exhibition. OnePetro
• 19. DeVries PM, Viégas F, Wattenberg M, Meade BJ (2018) Deep learning of aftershock patterns following large earthquakes. Nature 560:632–634
• 20. Ekinci YL, Balkaya Ç, Göktürkler G, Turan S (2016) Model parameter estimations from residual gravity anomalies due to simple-shaped sources using differential evolution algorithm. J Appl Geophys 129:133–147
• 21. Essa KS, Diab ZE (2022) Magnetic data interpretation for 2D dikes by the metaheuristic bat algorithm: sustainable development cases. Sci Rep 12(1):1–29. https://doi.org/10.1038/s41598-022-18334-1
• 22. Essa KS, Elhussein M (2017) A new approach for the interpretation of magnetic data by a 2-D dipping dike. J Appl Geophys 136:431–443
• 23. Essa KS, Elhussein M (2018) PSO (particle swarm optimization) for interpretation of magnetic anomalies caused by simple geometrical structures. Pure Appl Geophys 175:3539–3553
• 24. Essa KS, Elhussein M (2019) Magnetic interpretation utilizing a new inverse algorithm for assessing the parameters of buried inclined dike-like geological structure. Acta Geophys 67(2):533–544
• 25. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
• 26. Gay P (1963) Standard curves for interpretation of magnetic anomalies over long tabular bodies. Geophysics 28:161–200
• 27. Goyal S (2021) Evaluation metrics for regression models, analytics Vidhya. https://medium.com/analytics-vidhya/evaluation-metrics-for-regression-models91c65d73af
• 28. Guo W, Dentith MC, Li Z, Powell CM (1998) Self demagnetisation corrections in magnetic modelling: some examples. Explor Geophys 29(4):396–401
• 29. Hall B (2016) Facies classification using machine learning. Lead Edge 35(10):906–909
• 30. Haykin S (2009) Neural networks and learning machines. Prentice Hall, New York, p 938
• 31. Hood P (1964) The Königsberger ratio and the dipping-dyke equation. Geophys Prospect 12:440–456
• 32. Huang L, Dong X, Clee TE (2017) A scalable deep learning platform for identifying geologic features from seismic attributes. Lead Edge 36:249–256
• 33. Kara I (1997) Magnetic interpretation of two-dimensional dikes using integration-nomograms. J Appl Geophys 36:175–180
• 34. Kara I, Özdemir M, Ahmet Yüksel F (1996) Interpretation of magnetic anomalies of dikes using correlation factors. Pure Appl Geophys 147:777–788
• 35. 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. Geol Soc Spec Publ 101:43–58
• 36. Kitzig MC, Kepic A, Kieu DT (2017) Testing cluster analysis on combined petrophysical and geochemical data for rock mass classification. Explor Geophys 48:344–352
• 37. Ku CC, Sharp JA (1983) Werner deconvolution for automated magnetic interpretation and its refinement using Marquardt’s inverse modelling. Geophysics 48:754–774
• 38. Liu B, Guo Q, Li S, Liu B, Ren Y, Pang Y, Guo X, Liu L, Jiang P (2020) Deep learning inversion of electrical resistivity data. IEEE Trans Geosci Remote Sens 58:5715–5728
• 39. Liu X, Ge Q, Chen X, Li J, Chen Y (2021) Extreme learning machine for multivariate reservoir characterization. J Pet Sci Eng 205:108869
• 40. Manoj C, Nagarajan N (2003) The application of artificial neural networks to magnetotelluric time-series analysis. Geophys J Int 153:409–423
• 41. McGrath PH, Hood PJ (1970) The dipping dike case: A computer curve-matching method of magnetic interpretation. Geophysics 35:831–848
• 42. Mehanee SA (2014) Accurate and efficient regularized inversion approach for the interpretation of isolated gravity anomalies. Pure Appl Geophys 171:1897–1937
• 43. Mehanee S, Essa KS, Diab ZE (2021) Magnetic data interpretation using a new R-parameter imaging method with application to mineral exploration. Nat Resour Res 30(1):77–95
• 44. Mishra DC, Gupta SB, Rao MV, Venkatarayudu M, Laxman G (1987) Godavari basin-a geophysical study. J Geol Soc India 30:469–476
• 45. Radaideh MI, Surani S, O’Grady D, Kozlowski T (2019) Shapley effect application for variance-based sensitivity analysis of the few-group cross-sections. Ann Nucl Energy 129:264–279
• 46. Radhakrishna Murthy IV, Bangaru Babu S (2009) Magnetic anomalies across Bastar craton and Pranhita-Godavari basin in south of central India. J Earth Syst Sci 118:81–87
• 47. Radhakrishna Murthy IV, Visweswara Rao C, Krishna GG (1980) A gradient method for interpreting magnetic anomalies due to horizontal circular cylinders, infinite dykes and vertical steps. Proc Indian Acad Sci-Earth Planet Sci 89:31–42
• 48. Rao DA, Babu HR (1983) Quantitative interpretation of self-potential anomalies due to two-dimensional sheet-like bodies. Geophysics 48:1659–1664
• 49. Rao K, Biswas A (2021) Modeling and uncertainty estimation of gravity anomaly over 2D fault using very fast simulated annealing global optimization. Acta Geophys 69:1735–1751
• 50. 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 mineralization. J Earth Syst Sci 128:1–13
• 51. Reid AB, Allsop JM, Granser H, Millett AJ, Somerton IW (1990) Magnetic interpretation in three dimensions using Euler deconvolution. Geophysics 55:80–91
• 52. Roest WR, Verhoef J, Pilkington M (1992) Magnetic interpretation using the 3-D analytic signal. Geophysics 57(1):116–125
• 53. Sakrikar C, Deshpande K (2020) Use of machine learning and artificial intelligence in earth science. In: ICSITS–2020 Conference proceedings ICSITS. Int J Eng Res Technol (IJERT), 8(05)
• 54. Schmitt P, Veronez MR, Tognoli FMW, Todt V, Lopes RC, Silva CAU (2013) Electrofacies modelling and lithological classification of coals and mudbearing ingrained siliciclastic rocks based on neural networks. Earth Sci Res 2:193–208
• 55. Simpson TW, Poplinski JD, Koch PN, Allen JK (2001) Metamodels for computer-based engineering design: survey and recommendations. Eng Comput 17(2):129–150
• 56. Sobol IYM (1990) On sensitivity estimation for nonlinear mathematical models. Matematicheskoe Model 2(1):112–118
• 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(15):3903
• 58. Sundararajan N, Mohan NL, Raghava MS, Rao SV (1985) Hilbert transform in the interpretation of magnetic anomalies of various components due to a thin infinite dike. Pure Appl Geophys 123:557–566
• 59. Thanh Noi P, Kappas M (2018) Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors 18:18
• 60. Thompson DT (1982) EULDPH: A new technique for making computer-assisted depth estimates from magnetic data. Geophysics 47:31–37
• 61. Tlas M, Asfahani J (2015) The simplex algorithm for best-estimate of magnetic parameters related to simple geometric-shaped structures. Math Geosci 47:301–316
• 62. Tunkiel AT, Sui D, Wiktorski T (2020) Data-driven sensitivity analysis of complex machine learning models: a case study of directional drilling. J Pet Sci Eng 195:107630
• 63. Wang K, Zhang L (2008) Predicting formation lithology from log data by using a neural network. Pet Sci 5(3):242–246
• 64. Wrona T, Pan I, Gawthorpe RL, Fossen H (2018) Seismic facies analysis using machine learning. Geophysics 83:O83–O95
• 65. Xie F, Xiao C, Liu R, Zhang L (2017) Multi-threshold de-noising of electrical imaging logging data based on the wavelet packet transform. J Geophys Eng 14(4):900–908
• 66. Xu J, Li Y, Ren C, Wang S, Vanapalli SK, Chen G (2021) Influence of freeze-thaw cycles on microstructure and hydraulic conductivity of saline intact loess. Cold Reg Sci Technol 181:103183
• 67. Yuan S, Liu J, Wang S, Wang T, Shi P (2018) Seismic waveform classification and first-break picking using convolution neural networks. IEEE Geosci Remote Sens Lett 15(2):272–276
• 68. Yuan S, Jiao X, Luo Y, Sang W, Wang S (2022) Double-scale supervised inversion with a data-driven forward model for low-frequency impedance recovery. Geophysics 87(2):R165–R181
• 69. Zhou B, O’Brien G (2016) Improving coal quality estimation through multiple geophysical log analysis. Int J Coal Geol 167:75–92

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).