Fault detection using neural network

Elistia Liza Namigo


Fault detection technique using neural networks have been successfully applied to a seismic data volume. This technique  is basically creating  a volume that highlights faults by combining the information from several fault indicators attributes (i.e. similarity, curvature and energy) into fault occurrence probability. This is performed by training a neural network on  two sets of attributes extracted at sample  locations picked manually -  one set  represents the fault class and the other represents the non-fault class. The next step is to apply the trained artificial neural network on the seismic data. Result indicates that faults are more highlighted and have better continuity since the surrounding noise  are mostly suppressed.


fault detection; multi-attribute analysis; neural networks; fault cube.

Full Text:



Daber, R., A.Aqrawi, Schlumberger Limited. (2010). Petrel 2010: Interpreters Guide to Seismic Attributes.

Luo Y., W.G. Higgs, W.S.Kowalik (1995), Edge Detection and Stratigraphic Analysis Using 3D Seismic Data. SEG Expanded Abstract, 5.

Meldhal dkk. (1999). Survey Evaluation and Design: Prediction of Resolution Versus Line Interva. SEG 1999 Expanded Abstracts.

Odoh, B.I., Juliet Nneamaka Ilechukwu, Nnaemeka Ifeanyi Okoli. (2014). The Use of Seismic Attributes to Enhance Fault Interpretation of OT Field, Niger Delta. International Journal of Geosciences, 5, 826-834

Song, Jianguo, Xing Mu, Zhe Li, Changjiang Wang, Yongzhuang Sun. (2012). A Faults Identification Method Using Dip Guided Facet Model Edge Detector. SEG Technical Program Expanded Abstract. 1-5.

Zheng, Z.H., P. Kavousi, H. B. Di, (2014). Multi-Attributes and Neural Network-Based Fault Detection in 3D Seismic Interpretation", Advanced Materials Research, Vol. 838-841, 1497-1502.


  • There are currently no refbacks.