Features denoising-based learning for porosity classification

  • Jatin BediEmail author
  • Durga Toshniwal


Reservoir characterization is one of the most challenging tasks that help in modeling different lithological properties like porosity, permeability and fluid saturation using seismic readings like velocity profile, impedance, etc. Such a model is required for field development, placing new wells and prediction management. Seismic attributes are being progressively utilized for the tasks of model building, exploration and properties estimation from the data. However, these tasks become very complex due to the nonlinear and heterogeneous nature of subsurface properties. In this context, present work proposes a recurrent neural network-based learning framework to classify porosity using seismic attributes as predictor variables. The approach begins by calculating different seismic attributes from the data. From the initially calculated attribute set, features that are to be used for classification are selected by using two different strategies. Firstly, the seismic attributes having good correlation strength with reservoir porosity are extracted. Subsequently, generative topographic map is utilized to select the significant features. The final reduced features set obtained by the integrated result of above two strategies is then fed as an input to the empirical mode decomposition (EMD) algorithm. The denoised features resulting from the EMD algorithm are used to train the classification models. Further, a comparison is carried out between the proposed classification framework \((EMD+RNN)\) and other supervised classifiers to show the performance of the proposed framework.


Reservoir characterization Recurrent neural network Classification Petrophysical properties estimation 

List of symbols


State at timestamp t

\(W, U, V, W_\mathrm{f}, W_\mathrm{b}, W_\mathrm{o}\)

Weight parameters

\(b_\mathrm{f}, b_\mathrm{i}, b_\mathrm{i}\)

Bias parameters


Input at timestamp t


Output at timestamp t


Cell state at timestamp t


Output at previous timestamp

\(\sigma , \text {softmax}, \text {ReLU}\)

Activation functions


Input signal




Average of past gradients


Average of past squared gradients

\(\beta _1, \beta _2, \theta\)


\(m_t, v_t\)

Biased corrected parameters


Learning rate


Correlation coefficient



Funding was provided by Ministry of Human Resource Development.

Compliance with ethical standards

Conflict of interest

The author(s) declare(s) that there is no conflict of interest.


  1. 1.
    Lake LW Jr, Carroll HB (1986) Reservoir characterization, vol 1. Academic Press, CambridgeGoogle Scholar
  2. 2.
    Chopra S, Marfurt KJ (2007) Seismic attributes for prospect identification and reservoir characterization, vol 11. Society of Exploration Geophysicists Tulsa, OklahomaCrossRefGoogle Scholar
  3. 3.
    Kearey P, Brooks M, Hill I (2013) An introduction to geophysical exploration. Wiley, New YorkGoogle Scholar
  4. 4.
    Brown AR (2011) Interpretation of three-dimensional seismic data. Society of Exploration Geophysicists and American Association of Petroleum GeologistsGoogle Scholar
  5. 5.
    Robinson ES (1988) Basic exploration geophysicsGoogle Scholar
  6. 6.
    Tiab D, Donaldson EC (2015) Petrophysics: theory and practice of measuring reservoir rock and fluid transport properties. Gulf Professional Publishing, HoustonGoogle Scholar
  7. 7.
    Dake LP (2001) The practice of reservoir engineering (revised edition), vol 36. Elsevier, AmsterdamGoogle Scholar
  8. 8.
    Goodman HE (1995) Method for determining rock mechanical properties using electrical log data. US Patent 5,416,697Google Scholar
  9. 9.
    Dolberg DM, Helgesen J, Hanssen TH, Magnus I, Saigal G, Pedersen BK (2000) Porosity prediction from seismic inversion, Lavrans Field, Halten Terrace, Norway. Lead Edge 19(4):392–399CrossRefGoogle Scholar
  10. 10.
    Gastaldi C, Biguenet JP, De Pazzis L (1997) Reservoir characterization from seismic attributes: an example from the peciko field (Indonesia). Lead Edge 16(3):263–266CrossRefGoogle Scholar
  11. 11.
    Hampson DP, Schuelke JS, Quirein JA (2001) Use of multiattribute transforms to predict log properties from seismic data. Geophysics 66(1):220–236CrossRefGoogle Scholar
  12. 12.
    Chopra S, Marfurt KJ (2005) Seismic attributes a historical perspective. Geophysics 70(5):3SO–28SOCrossRefGoogle Scholar
  13. 13.
    White RE (1991) Properties of instantaneous seismic attributes. Lead Edge 10(7):26–32CrossRefGoogle Scholar
  14. 14.
    Russell B, Hampson D, Schuelke J, Quirein J (1997) Multiattribute seismic analysis. Lead Edge 16(10):1439–1444CrossRefGoogle Scholar
  15. 15.
    Van der Baan M, Jutten C (2000) Neural networks in geophysical applications. Geophysics 65(4):1032–1047CrossRefGoogle Scholar
  16. 16.
    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(4):431–444. CrossRefGoogle Scholar
  17. 17.
    Dorrington KP, Link CA (2004) Geneticalgorithm/neuralnetwork approach to seismic attribute selection for welllog prediction. Geophysics 69(1):212–221CrossRefGoogle Scholar
  18. 18.
    Parra JO, Iturrarn-Viveros U, Parra JS, Xu PC (2014) Neural network and rock physics for predicting and modeling attenuation logs. In: SEG technical program expanded abstracts. Society of Exploration Geophysicists, pp 633–637Google Scholar
  19. 19.
    Chaki S, Verma AK, Routray A, Mohanty WK, Jenamani M (2016) A novel framework based on SVDD to classify water saturation from seismic attributes. CoRR
  20. 20.
    Verma AK, Chaki S, Routray A, Mohanty WK, Jenamani M (2014) Quantification of sand fraction from seismic attributes using neuro-fuzzy approach. J Appl Geophys 111:141–155CrossRefGoogle Scholar
  21. 21.
    Naimi S, Shadizadeh S, Riahi M, Mirzakhanian M (2014) Estimation of reservoir porosity and water saturation based on seismic attributes using support vector regression approach. J Appl Geophys 107:93–101CrossRefGoogle Scholar
  22. 22.
    Mojeddifar S, Kamali G, Ranjbar H (2015) Porosity prediction from seismic inversion of a similarity attribute based on a pseudo-forward equation (PFE): a case study from the North Sea Basin, Netherlands. Pet Sci 12(3):428–442CrossRefGoogle Scholar
  23. 23.
    Rafik B, Kamel B (2017) Prediction of permeability and porosity from well log data using the nonparametric regression with multivariate analysis and neural network, Hassi R’Mel Field, Algeria. Egypt J Pet 26(3):763–778CrossRefGoogle Scholar
  24. 24.
    Elkatatny S, Mahmoud M, Tariq Z, Abdulraheem A (2018) New insights into the prediction of heterogeneous carbonate reservoir permeability from well logs using artificial intelligence network. Neural Comput Appl 30(9):2673–2683CrossRefGoogle Scholar
  25. 25.
    Lopes RL, Jorge AM (2018) Assessment of predictive learning methods for the completion of gaps in well log data. J Pet Sci Eng 162:873–886CrossRefGoogle Scholar
  26. 26.
    Jamalian M, Safari H, Goodarzi M (2018) Permeability prediction using artificial neural network and least square support vector machine methods. In: 80th EAGE conference and exhibition 2018Google Scholar
  27. 27.
    Zahmatkesh I, Kadkhodaie A, Soleimani B, Golalzadeh A, Azarpour M (2018) Estimating Vsand and reservoir properties from seismic attributes and acoustic impedance inversion: a case study from the Mansuri oilfield, SW Iran. J Pet Sci Eng 161:259–274CrossRefGoogle Scholar
  28. 28.
    Ahmadi MA, Chen Z (2018) Comparison of machine learning methods for estimating permeability and porosity of oil reservoirs via petro-physical logs. Petroleum. Google Scholar
  29. 29.
    Christopher M, Svensn Markus, Williams Christopher KI (1998) GTM: the generative topographic mapping. Neural Comput 10(1):215–234CrossRefGoogle Scholar
  30. 30.
    Tan PN, Kumar V (2006) Introduction to data mining. Pearson Education India, New DelhiGoogle Scholar
  31. 31.
    Mandic DP (2001) Chambers: recurrent neural networks for prediction: learning algorithms, architectures and stability. Wiley, New YorkCrossRefGoogle Scholar
  32. 32.
    Seismic data repository. Accessed 10 Nov 2017
  33. 33.
    Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In: Proceedings of the royal society of london a: mathematical, physical and engineering sciences, vol 454. The Royal Society, pp 903–995Google Scholar
  34. 34.
    Gaur P, Pachori RB, Wang H, Prasad G (2018) A multi-class EEG-based bci classification using multivariate empirical mode decomposition based filtering and riemannian geometry. Expert Syst Appl 95:201–211CrossRefGoogle Scholar
  35. 35.
    Bedi J, Toshniwal D (2018) Empirical mode decomposition based deep learning for electricity demand forecasting. IEEE Access 6:49144–49156CrossRefGoogle Scholar
  36. 36.
    Famili A, Shen WM, Weber R, Simoudis E (1997) Data preprocessing and intelligent data analysis. Intell Data Anal 1(1):3–23CrossRefGoogle Scholar
  37. 37.
    Gibson I, Amies C (2001) Data normalization techniques. US Patent 6,259,456Google Scholar
  38. 38.
    Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3(Mar):1157–1182zbMATHGoogle Scholar
  39. 39.
    Hall MA (1999) Correlation-based feature selection for machine learning. PhD thesis, The University of WaikatoGoogle Scholar
  40. 40.
    Bedi J, Toshniwal D (2018) Attribute selection based on correlation analysis. Advances in big data and cloud computing. Springer, Singapore, pp 51–61CrossRefGoogle Scholar
  41. 41.
    Bedi J, Toshniwal D (2018) SFA-GTM: seismic facies analysis based on generative topographic map and RBF. arXiv preprint arXiv:1806.00193
  42. 42.
    Premanode B, Vonprasert J, Toumazou C (2013) Prediction of exchange rates using averaging intrinsic mode function and multiclass support vector regression. Artif Intell Res 2(2):47CrossRefGoogle Scholar
  43. 43.
    Kingma, Diederik P, Jimmy Ba (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
  44. 44.
    Gunn SR (1998) Support vector machines for classification and regression. ISIS Tech Rep 14(1):5–16Google Scholar
  45. 45.
    Nasrabadi NM (2007) Pattern recognition and machine learning. J Electron Imaging 16(4):049901MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of CSEIndian Institute of Technology (IIT), RoorkeeRoorkeeIndia

Personalised recommendations