Abstract
Magnetic surveys have been used for mineral exploration where different data processing techniques were used to derive the parameters of causative targets. In this respect, the neural network (NN) technique was used to estimate the magnetic causative target parameters. Examples of NN inversion have been tested on synthetic examples where the NN was trained well using forward models of the vertical magnetic effect of a vertical sheet and a horizontal circular cylinder. Specifically, modular neural network (MNN) inversion has been used for the parameter estimation of the causative targets, where the sigmoid function was used as the activation function. The effect of random noise and the error estimation of the horizontal location have been analyzed. When NN is applied to real data, it estimates successfully the parameters of the causative targets such as burial depths, magnetic constants, and angle of polarization. Hilbert transform has been used to locate the source origin, which is important for the NN inversion. This approach has more advantages than the conventional data inversions in terms of its efficiency and flexibility. It also gives fast solutions. The MNN approach has been applied to the Kursk and Manjampalli anomalies, where the results were shown to be in good agreement with the other techniques published in the literature.
Abstract
تستعمل المساحة المغناطیسیة للاستكشاف عن المعادن باستخدام الطرق المختلفة لمعالجة المعلومات ومن ثم لاستنباط المعاملات للاھداف المسببة للمغناطیسیة منھا.وفي ھذا الاطار استخدمت الشبكة العصبیة لتقدیر تلك المعاملات. وقد تم اختبار الحلول التعاكسیة على الامثلة المصطنعة للاجسام المسببة للمغناطیسیة وذلكباستخدام الشبكة العصبیة بعد تدریبھا تدریبا جیدا على النماذج المسببة للمغناطیسیة العمودیة لصفیحة رأسیة واسطوانیة افقیة ذات مقطع دائري.وقد استعملت الشبكةالعصبیة التي تمت معایرتھا للقیام بالحل التعاكسي لتقدیر المعلومات عن كما تم دراسة وتحلیل كلا من تاثیر .(S) الاجسام المسببة للمغناطیسیة مع استخدام الدالة المنشطة على ھیئة حرف الضوضاء العشوائیة والخطأ في تحدید المواقع الافقیة للاھداف المسببة للمغناطیسة. وقد تم بنجاح تطبیق الحل التعاكسي على البیانات الحقلیة باستخدام الشبكة العصبیة في تقدیر المعاملات للاھداف المسببة للمغناطیسیة كالاعماق والثوابت المغناطیسیة وزوایا الاستقطاب. واستخدم تحویل ھلبرت المھم لتحدید الموقع الافقي للاھداف المسببة للمغناطیسیة. أن الحلالتعاكسي باستخدام الشبكة العصبیة لھو افضل حل اذا ماقورن بالحلول التعاكسیة الاخرى وذلك من حیث فعالیتة ومرونتة وسرعة الحصول على النتائج منھ.فطریقة الحل التعاكسي باستخدام الشبكة العصبیة قد طبقت على كل من شاذة كیرسك وشاذة مانجمبالي، حیث اظھرت النتائجتوافقاجیدا مع نتائجالتقنیات الاخرى المنشورة.
Similar content being viewed by others
References
Barbosa VCF, Silva JBC, Medeiros WE (1999) Stability analysis and improvement of structural index estimation in Euler deconvolution. Geophysics 64:48–60
Baum EB, Haussler D (1989) What size network gives valid generalization?. Neural Comp 1:151–160
Bescoby DJ, Cawley GC, Chroston PN (2006) Enhanced interpretation of magnetic survey data from archaeological sites using artificial neural networks. Geophysics 71:H45–H53
Bishop CM (1995) Training with noise is equivalent to Tikhonova regularization. Neural Comp 7:108–116
Calderόn-Macías C, Sen MK, Stoffa PL (2000) Artificial neural networks for parameter estimation in geophysics. Geophys Prospect 48:21–47
Dondurur D, Pamukçu OA (2003) Interpretation of magnetic anomalies from dipping dike model using inverse solution, power spectrum and Hilbert transform methods. J Balkan Geophys Soc 6:127–136
El-Kaliouby H (2001) Extracting IP parameters from TEM data. In: Poulton MM (ed) Computational neural networks for geophysical data processing. Pergamon, Oxford chapter 17
El-Kaliouby H, Poulton M (1999) Inversion of coincident loop TEM data for layered polarizabe ground using neural networks. Society of Exploration Geophysicists (SEG) 69th annual meeting, Houston, 31 October–5 November 1999
El-Qady G, Ushijima K (2001) Inversion of DC resistivity data using neural networks. Geophys Prospect 49:417–430
Fossati M, Zerilli A, Ronchini G, Apollono B (1992) Lineament analysis for potential field data using neural network: 62nd Annual International Meeting, SEG, Expanded Abstracts: 6–9
Grant FS, West GF (1965) Interpretation theory in applied geophysics. McGraw-Hill, New York, pp 324–337
Guo Y, Hansen R, Harthil N (1992) Feature recognition from potential fields using neural networks. 62nd Annual International Meeting, SEG, Expanded Abstracts, 1–5
Helle HB, Bhatt A, Ursin B (2001) Porosity and permeability prediction from wireline logs using artificial neural networks: A North Sea case study. Geophys Prospect 49:431–444
Johnson WW (1969) A least squares method of interpreting magnetic anomalies caused by two dimensional structures. Geophysics 34:65–74
Khurana KK, Rao SVS, Pal PC (1981) Frequency domain least squares inversion of thick dike magnetic anomalies using Marquardt algorithm. Geophysics 46:1745–1748
Macias C, Sen M, Stoffa P (2000) Artificial neural networks for parameter estimation in geophysics. Geophys Prospect 48:21–47
Mohen NL, Sundararajan N, Seshagiri Rao SV (1982) Interpretation of some two-dimensional magnetic bodies using Hilbert transform. Geophysics 47:376–387
Nabighian MN (1972) The analytic signal of two-dimensional magnetic bodies with polygonal cross-section, its properties and use for automated anomaly interpretation. Geophysics 37:507–512
Poulton MM (2001) Computational neural networks for geophysical data processing. Pergamon, Oxford
Poulton MM (2002) Neural networks as an intelligence amplification tool: A review of applications. Geophysics 67:979–993
Poulton MM, Sternberg BK, Glass CE (1992a) Location of subsurface targets in geophysical data using neural networks. Geophysics 57:1534–1544
Poulton MM, Sternberg BK, Glass CE (1992b) Neural network pattern recognition of subsurface EM images. J Appl Geophys 29:21–36
Radhakrishna Murthy IV, Vesweswsra Rao C, Gobalakrishna G (1980) A gradient method for interpreting magnetic anomalies due to horizontal circular cylinder, infinite dikes and vertical steps. Proc Indian Acad Sci Earth Planet Sci 89:31–42
Raiche A (1991) A pattern recognition approach to geophysical inversion using neural nets. Geophys J Int 105:629–648
Rao BSR, Murthy IVR, Rao CV (1973) Two methods for computer interpretation of magnetic anomalies of dike. Geophysics 38:710–718
Spichak V, Popova I (2000) Artificial neural networkinversion of magnetotelluric data in terms of three-dimensional earth macrparameters. Geophys J Int 142:15–26
Sudhakar KS, Rao RPR, Murthy RIV (2004) Modified Werner deconvolution for iversion of magnetic anomalies of horizontal circular cylinders. J Ind Geophys Union 8:179–183
Thomas JB (1969) An introduction to statistical communication theory. Wiley, New York, pp 639–657
Ucan ON, Bilgili E, Albora AM (2002) Magnetic anomaly separation using genetic cellular neural networks. J Balkan Geophys Soc 5:65–70
Van der Baan M, Jutten C (2000) Neural networks in geophysical applications. Geophysics 65:1032–1047
Werner S (1953) Interpretation of magnetic anomalies at sheet like bodies. Ser. C. 508. Sveriges Geologiska Undersok, Stockholm
Won IJ (1981) Application of Gauss’s method to magnetic anomalies of dipping dikes. Geophysics 46:211–215
Zhang Q, Gupta K (2000) Neural networks for RF and microwave design. Artech House, London
Zhang L, Poulton MM, Wang T (2002) Borehole electrical resistivity modeling using neural networks. Geophysics 67:1790–1797
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Al-Garni, M.A. Interpretation of some magnetic bodies using neural networks inversion. Arab J Geosci 2, 175–184 (2009). https://doi.org/10.1007/s12517-008-0026-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12517-008-0026-9