Abstract
Porosity plays an important part of understanding permeability and fluid flow within the continental, crystalline rocks. Geophysical well logs are presently the most consistent means of providing continuous information for porosity estimation. However, it is difficult to interpret geophysical well logs data in crystalline rocks due to their complex geological features and the difficulty in understanding and using the complex and intensive information content in these data. Motived by the successful prediction abilities of artificial neural networks (ANN) to solve different problems in geophysics, this study explore the applicability of using ANNs to predict porosity in continental, crystalline rocks. This ANN technique is calibrated on Chinese Continental Scientific Drilling Main Hole (CCSD-MH) data, which provides core porosity data combined with four geophysical well logs (density, neutron porosity, sonic and resistivity). The data from CCSD-MH is utilized to train feed-forward backpropagation (FFBP) neural network and radial basis function (RBF) neural network to derive a relationship between geophysical well logs and porosity, and hence predict porosity accurately. The findings demonstrate that ANNs provide better performances with sets of three geophysical well logs (density, sonic and resistivity) than regression technique. Comparison of FFBP to RBF showed that RBF reveals better stability and more accurate performances than FFBP. Based on the success achieved in this study, this intelligence artificial technique can be a very advantageous tool in facilitating the task of geophysicists in the framework of research drillings in continental crust.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Aiken L.S. and West S.G., 1991. Multiple Regression: Testing and Interpreting Interactions. Sage Publ. Inc., Thousand Oaks, CA.
Anderson T.W., 1984. An Introduction to Multivariate Statistical Analysis. 2nd Edition. John Wiley&Sons, New York.
Anderson R.N., Alt J.C., Malpas J., Lovell M.A., Harvey P.K. and Pratson E.L., 1990. Geochemical well logging in basalts: The palisade sill and the oceanic crust of hole 504B. J. Geophys Res., 90, 9265–9292.
Baddari K., Aifa T., Djarfour N. and Ferahtia J., 2009. Application of a radial basis function artificial neural network to seismic data inversion. Comput. Geosci., 35, 2338–2344.
Baldwin J.L., Bateman A.R.M. and Wheatley C.L., 1990. Application of neural networks to the problem of mineral identification from well-logs. The Log Analyst, 3, 279–293.
Bartetzko A., Delius H. and Pechnig R., 2005. Effect of compositional and structural variations on log responses of igneous and metamorphic rocks. I: mafic rocks. In: Harvey P.K., Brewer T.S., Pezard P.A. and Petrov V.A (Eds), Petrophysical Properties of Crystalline Rocks. Geol. Soc. London Spec. Publ., 240, 255–278.
Benaouda D., Wadge G., Whitmarsh R.B., Rothwell R.G. and MacLeod C., 1999. Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program. Geophys. J. Int., 136, 477–491.
Benoudjit N. and Verleysen M., 2003, On the kernel widths in radial-basis function networks. Neural Process. Lett., 18, 139–154.
Bhatt A., 2002. Reservoir Properties from Well Logs Using Neural Networks. Ph.D. Thesis, Norwegian University of Science and Technology, Trondheim, Norway.
Bhatt A. and Helle H.B., 2002. Committee neural networks for porosity and permeability prediction from well logs. Geophys. Prospect., 50, 645–660.
Bishop C., 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford, U.K.
Celikoglu H.B., 2006. Application of radial basis function and generalized regression neural networks in non-linear function specification for travel mode choice modelling. Math. Comput. Model., 44, 640–658.
Chang H.C., Merkel Kopaska D.C., Chen H.C. and Durrans S.R., 2000. Lithofacies identification using multiple adaptive resonance theory neural networks and group decision expert system. Comput. Geosci., 26, 591–601.
Dreiseitl S. and Ohno-Machado L., 2002. Logistic regression and artificial neural network classification models: a methodology review. J. Biomed. Inform., 35, 352–359.
Good P.I., 2006. Resampling Methods. 3rd Edition. Birkhauser, Boston, PA.
Hagan M.T. and Menhaj M.B., 1994. Training feedforward techniques with the Marquardt algorithm. IEEE Trans. Neural Netw., 5, 989–993.
Harvey P.K., Brewer T.S., Pezard P.A. and Petrov V.A. (Eds), 2005. Petrophysical Properties of Crystalline Rocks. Geol. Soc. London Spec. Publ., 240.
Haykin S., 1998. Neural Networks: A Comprehensive Foundation. Prentice-Hall, New Jersey.
Helle H.B., Bhatt A. and Ursin B., 2001. Porosity and permeability prediction from wireline logs using artificial neural networks: a North Sea case study. Geophys. Prospect., 49, 431–444.
Hornik K., Stinchcombe M.B. and White H., 1989. Multilayer feed-forward networks are universal approximators. Neural Netw., 2, 359–366.
Ji S.C. and Xu Z.Q., 2009. Drilling deep into the ultrahigh pressure (UHP) metamorphic terrane. Tectonophysics, 475, 201–203.
Ji S.C., Wang Q., Marcotte D., Salisbury M.H. and Xu Z.Q., 2007. P-wave velocities, anisotropy and hysteresis in ultrahigh-pressure metamorphic rocks as a function of confining pressure. J. Geophys. Res., 112, B09204, DOI: 10.1029/2006JB004867.
Kern H., Jin Z.M., Shan Gao S., Popp T. and Xu Z., 2002. Physical properties of ultrahigh-pressure metamorphic rocks from the Sulu terrain, eastern central China: implications for the seismic structure at the Donghai (CCSD) drilling site.Tectonophysics, 354, 315–330.
Levenberg K., 1944. A method for the solution of certain non-linear problems in least squares. Q. Appl. Math., 2, 164–168.
Liu J., Wu S. and Zidek J.V., 1997. On segmented multivariate regression. Stat. Sin., 7, 497–525.
Liu F.L., Xue H.M., Xu Z.Q., Liang F.H. and Gerdes A., 2006. SHRIMP U-Pb zircon dating from eclogite lens in marble, Shuanghe area of Dabie UHP terrane: restriction on prograde, UHP and retrograde metamorphic ages. Acta Petrol. Sinica, 22, 1761–1778.
Liu Q., Zeng Q., Zheng J., Yang T., Qiu N., Liu Z., Luo Y. and Jin Z., 2010. Magnetic properties of serpentinized garnet peridotites from the CCSD main hole in the Sulu ultrahigh-pressure metamorphic belt, eastern China. J. Geophys. Res, 115, B06104, DOI: 10.1029/2009JB000814.
Lopez G., Batlles F.J. and Tovar-Pescador J., 2005. Selection of input parameters to model direct solar irradiance by using artificial neural networks. Energy, 30, 1675–1684.
Luo M. and Pan H.P, 2010. Well logging responses of UHP metamorphic rocks from CCSD Main Hole in Sulu Terrane, Eastern Central China. J. Earth Sci., 21, 347–357, DOI: 10.1007/s12583-010-0098-9.
Luo M. and Pan H.P., 2011. Resistivity logs of the Chinese Continental Scientific Drilling Main Hole: implication for the crustal electrical structure of Dabie-Sulu Terrane, Central-Eastern China. J. Earth Sci., 22, 292–298, DOI: 10.1007/s12583-011-0182-9.
Luthi S.M. and Bryant I.D., 1997. Well-log correlation using a back-propagation neural network. Math. Geol., 29, 413–425.
Maiti S., Tiwari R.K. and Kumpel H.J., 2007. Neural network modelling and classification of lithofacies using well log data: a case study from KTB borehole site. Geophys. J. Int., 169, 733–746.
Maiti S. and Tiwari R.K., 2009. A hybrid Monte Carlo method based artificial neural networks approach for rock boundaries identification: a case study from KTB Borehole. Pure Appl. Geophys., 166, 2059–2090, DOI: 10.1007/s00024-009-0533-y.
Maiti S. and Tiwari R.K., 2010. Neural network modeling and an uncertainty analysis in Bayesian framework:A case study from the KTB borehole site. J. Geophys. Res., 115, B10208, DOI: 10.1029/2010JB000864.
May R.J., Maier H.R. and Dandy G.C., 2010. Data splitting for artificial neural networks using SOM- based stratified sampling. Neural Netw., 23, 283–294.
Meng X.H., Yu Q.F., Guo Y.Z. and Zhou Y.X., 2007. A preliminary study on paleomagnetism and rock magnetism of Eclogite from the Maobei area. J. China Univ. Geosci., 18, 366–374.
Montgomery D.C., Peck E.A., Vining G.G., 2006. Introduction to Linear Regression Analysis, 4th edition, Wiley-Interscience Publication.
Moody J. and Darken C.K., 1989. Fast learning in networks of locally-turned processing units. Neural Comput., 1, 281–294.
Moos D., 1990. Utilization of observations of well bore failure to constrain the orientation and magnitude of crustal stresses: Application to continental, Deep Sea Drilling Project, and Ocean Drilling Program boreholes. J. Geophys Res., 95(B6), 9305–9325.
Moritz E., Bornholdt S., Westphal H. and Meschede M., 2000. Neural network interpretation of LWD data (ODP Leg 170) confirms complete sediment subduction at the Costa Rica convergent margin. Earth Planet. Sci. Lett., 174, 301–331.
Muggeo V.M.R., 2003. Estimating regression models with unknown break-points. Statist. Med., 22, 3055–3071, DOI: 10.1002/sim.1545.
Niu X.Y., Pan H.P., Wang W.X., Zhu L.F. and Xu D.H., 2004. Geophysical well logging in main hole (0–2000 m) of Chinese Continental Scientific Drilling. Acta Petrol. Sin., 20, 109–118 (in Chinese with English abstract).
Ou X.G., Jin Z.M., Xia B., Xu H.J. and Jin S.Y., 2005. Correlations between petrophysical properties of the UHP rocks and its significance on establishing the geophysical interpretation standards for crystalline rocks. Acta Petrol. Sin., 21, 1005–1014.
Pan H.P., Luo M. and Zhao Y., 2010. Identification of metamorphic rocks in the CCSD Main Hole. In: Yue S., Wei H.L., Wang L. and Song Y. (Eds), 2010 Sixth International Conference on Natural Computation. IEEE, 4049–4051.
Pan H.P., Niu, Y.X. and Wang W.X., 2002. CCSD well logging engineering program. J. China Univ. Geosci., 13, 91–94.
Pan H.P., Niu Y.X. and Wang W.X., 2005. Radioactive logging application in CCSD Main Hole. Earth Sci.-J. China Univ. Geosci., 30(Suppl.), 49–56 (in Chinese with English Abstract).
Park J. and Sandberg I., 1993. Approximation and radial basis function networks. Neural Comput., 5, 305–316.
Pechnig R., Delius H. and Bartetzko A., 2005. Effect of compositional variations on log responses of igneous and metamorphic rocks. II: acid and intermediate rocks. In: Harvey P.K., Brewer T.S., Pezard P.A. and Petrov V.A. (Eds), Petrophysical Properties of Crystalline Rocks. Geol. Soc. London Spec. Publ., 240, 279–300.
Pechnig R., Heaverkamp S. and Wohlenberg J., 1997. Integrated log interpretation in the German Continental Deep Drilling Program: lithology, porosity, and fracture zones. J. Geophys Res., 102(B8), 8363–18390.
Poulton M.M., 2002. Neural networks as an intelligence amplification tool: A review of applications. Geophysics, 67, 979–993.
Pratsone E.L., Anderson R.N., Dove R.E., Lyle M., Silver L.T., James E.J. and Chappell B.W., 1992. Geochemical logging in the Cajon Pass drillhole and a new, oxide, igneous rock classification scheme. J. Geophys Res., 97, 5167–5180.
Reynaldi A., Lukas S. and Margaretha H., 2012. Backpropagation and Levenberg-Marquardt algorithm for training finite element neural network. In: El-Dabass E., Debono C., Muscat R., Adithia N., Basuki T. and Orsoni A. (Eds), Proceedings, UKSim-AMSS, 6th European Modelling Symposium. IEEE, 89–94, DOI: 10.1109/EMS.2012.56.
Seber G.A.F. and Wild C.J., 1989. Nonlinear Regression. John Wiley&Sons, New York.
Serra O., 2007. Well Logging and Reservoir Evaluation. Editions Technip, Paris, France.
Shao J. and Tu D., 1995. The Jackknife and Bootstrap. Springer-Verlag, New York.
Sun S.S., Ji S.C., Wang Q., Salisbury M. and Kern H., 2012. P-wave velocity differences between surface-derived and core samples from the Sulu ultrahigh-pressure terrane: Implications for in situ velocities at great depths. Geology, 40, 651–654, DOI: 10.1130/G33045.
Tullborg E.L. and Larson S.A, 2006. Porosity in crystalline rocks — a matter of scale. Eng. Geol., 84, 75–83.
Van der Baan M. and Jutten C., 2000. Neural networks in geophysical applications. Geophysics, 65, 1034–1047.
Wang Q., Ji S.C., Salisbury M.H., Xia B., Pan M.B. and Xu Z.Q., 2004. Pressure dependence and anisotropy of P-wave velocities in ultrahigh-pressure metamorphic rocks from the Dabie-Sulu orogenic belt (China): Implications for seismic properties of subducted slabs and origin of mantle reflections. Tectonophysics, 398, 67–99.
White H., 1992 Artificial Neural Networks. Approximation and Learning Theory. Blackwell, Cambridge, MA.
Xu P.F., Liu F.T., Wang Q.C., Cong B.L., Chen H. and Sun R.M., 2000. Seismic tomography beneath the Dabie-Sulu collision orogeny — 3D velocity structures of lithosphere. Chin. J. Geophys., 43, 377–385 (in Chinese with English Abstract).
Xu S., Okay A.I., Ji S., Sengor A.M.C., Su W., Liu Y. and Jiang L., 1992. Diamond from the Dabie Shan metamorphic rocks and its implication for tectonic setting. Science, 256, 80–82.
Xu Z.Q., Yang W.C., Ji S.C., Zhang Z.M., Yang J.S., Wang Q. and Tang Z.M., 2009. Deep root of a continent-continent collision belt: Evidence from the Chinese Continental Scientific Drilling (CCSD) deep borehole in the Sulu ultrahigh-pressure (HP-UHP) metamorphic terrane, China. Tectonophysics, 475, 204–219.
Yang W.C., 2009. The crust and upper mantle of the Sulu UHPM belt. Tectonophysics, 475, 226–234.
Zimmermann G., Burkhardt H. and Meichert M., 1992. Estimation of porosity in crystalline rock by a multivariate statistical approach. Sci. Drill., 3, 27–37.
Zoveidavianpoor M., Samsuri A. and Shadizadeh S.R., 2013. Prediction of compressional wave velocity by an artificial neural network using some conventional well logs in a carbonate reservoir. J. Geophys. Eng., 10, 045014, 1–13, DOI: 10.1088/1742-2132/10/4/045014.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Konaté, A.A., Pan, H., Khan, N. et al. Prediction of porosity in crystalline rocks using artificial neural networks: An example from the Chinese Continental Scientific Drilling Main hole. Stud Geophys Geod 59, 113–136 (2015). https://doi.org/10.1007/s11200-013-0993-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11200-013-0993-5