DOI: 10.5176/2251-2179_ATAI8
Authors: Muhammad Abdulkarim, Wan Fatimah Wan Ahmad and Afza Shafie, Radzuan Razali
Abstract:
Controlled Source Electro-Magnetic (CSEM) sounding technique which is an alternative name for Sea Bed Logging (SBL) is a recent effective resistivity sensing technology used in finding, testing and evaluating hydrocarbon reservoirs. Both sea water and hydrocarbon (target) depths can cause a significant impact when analyzing and interpreting data from CSEM environment. This paper looks at the feasibility of applying artificial neural network to the scaled marine environment data for finding and evaluating hydrocarbon reservoirs. Artificial Neural Network (ANN) is non-linear predictive models that resemble biological neural network in structure and learn through process of training. One of the advantage of ANN is the ability to be used as an arbitrary function approximation mechanism which ‘learns’ from observed data. Data collected from the experiments of different depths and target positions are used to obtain the neural network training model, while Mean Square Error is for model accuracy evaluation. Preliminary results show that the Artificial Neural Network has a potential in modeling the CSEM environment.
Keywords: Artificial Neural Network; Controlled Source Electro-Magnetic; Hydro-Carbon Reservoirs
Updating...