Enhancement of fault interpretation using multi-attribute analysis and artificial neural network (ANN) approach: a case study from Taranaki Basin, New Zealand Priyadarshi Chinmoy Kumar 1 Animesh Mandal 2,3 1 CSIR-National Geophysical Research Institute, Hyderabad 500007, India. 2 Department of Earth Sciences, Indian Institute of Technology, Kanpur 208016, India. 3 Corresponding author. Email: animeshm@iitk.ac.in Abstract. Enhanced seismic data conditioning and multi-attribute analysis through non-linear neural processing workflows has been applied to 3D seismic data over 215.10 km 2 area of the Opunake prospect located in the south-eastern offshore Taranaki Basin. The present work aims to delineate faults and the related detail of structural features from the study area. Post-stack seismic data conditioning techniques such as dip-steering and structural filtering are applied to enhance the lateral continuity of seismic events and eliminate random noises from the data with the objective of improving the visibility of faults in the data volume. The conditioned data is then used to extract several attributes, such as similarity, dip variance, curvature, energy and frequency, that act as potential contributors for enhancing the fault visibility. A fully connected multilayer perceptron (MLP) network is developed to choose the proper combination of attributes for fault detection. These seismic attributes (known as the test datasets) are then trained at identified fault and non-fault locations using this network. The network comprises of 11, 7, and 2 nodes in the input layer, hidden layer and output layer, respectively. The neural training resulted in an overall minimum root mean square (RMS) misfit and misclassification (%) ranging from 0.54 to 0.67 and 18.67 to 10.42, respectively, between the trained and the test datasets. The neural training generates a fault probability attribute that produces an improved fault visibility capturing the minute details of the seismic volume as compared with the results of individual seismic attribute. Thus, the present work demonstrates an enhanced and robust workflow of fault prediction and visualisation for detail structural interpretation from 3D seismic data volume. Key words: 3D visualisation, attributes, fault probability cube, interpretation, neural network. Received 25 June 2016, accepted 17 May 2017, published online 3 August 2017 Introduction Seismic attribute analysis contributes significantly in the success of 3D seismic interpretation workflows in the petroleum industry. Its analysis brings out an enhanced interpretation of the subsurface geology and reservoir property by defining their structural and depositional environment. Thus, deciphering detailed structural features hidden within the data by the use of seismic attributes is an important approach for understanding the subsurface structural configuration, as well as monitoring the static and dynamic behaviour of the reservoir. Over the past two to three decades several seismic attributes have been defined for imaging structural aspects from seismic data. Some of these include, seismic coherency (Bahorich and Farmer, 1995; Marfurt et al., 1998, 1999), similarity (Tingdahl, 1999; Tingdahl et al., 2001; Tingdahl and de Rooij, 2005), dip and azimuth (Luo et al., 2002; Chopra and Marfurt, 2007; Kumar, 2016), volumetric curvature (Roberts, 2001; Al-Dossary and Marfurt, 2006) and other attributes (Chopra and Marfurt, 2007). These attributes mostly define the geometrical and structural characteristics, e.g. shape, angle and continuity, of the seismic events. Thus, they deliver a substantial contribution for interpreting geological structures, such as, faults, folds, fracture networks from seismic data. Imaging and analysing these structural complexities of the subsurface provides clues for understanding several key facts related to reservoir geology, e.g. position of juxtaposed beds that control the sealing mechanism across the geological structures, identification of plausible trapping zones for hydrocarbon bearing sediments, and indication of structural arrangement of subsurface reservoir. This kind of analysis also helps to estimate the storage and migration of hydrocarbon resources in the subsurface. However, identification of these structural complexities from the subsurface and their seamless interpretation is an important and challenging task for seismic interpreters. The advent of 3D seismic visualisation and advanced attribute processing techniques have helped the interpreters to take up these challenges and contribute towards successful structural interpretation from seismic data. However, interpreters very often encounter difficulties in imaging geologic structures from the data. It is due to the fact that these features are characterised by discontinuous seismic reflections and are most commonly obscured by seismic noises, e.g. dispersion effects, diffractions etc. Thus, a robust data conditioning technique and attribute analysis workflow is needed to bring out an enhanced image of these complex structural features by suppressing the noise level. In the context of attribute analysis, proper selection of a set of structural attributes plays significant role as no single attribute effectively images these structural complexities. Thus, a set of logically chosen attributes is needed to generate a better and more accurate image of complex geological structures. This CSIRO PUBLISHING Exploration Geophysics, 2018, 49, 409–424 http://dx.doi.org/10.1071/EG16072 Journal compilation Ó ASEG 2018 www.publish.csiro.au/journals/eg