![introduction to artificial neural network by zurada pdf printer introduction to artificial neural network by zurada pdf printer](https://images-na.ssl-images-amazon.com/images/I/71SShymRGVL.jpg)
Sonic wave velocities of carbonate rocks seem to be highly influenced by heterogeneity, and particularly by texture and porosity type (Weger et al 2009). Frankly speaking, the contribution of sonic wave velocity to the upstream oil and gas industry is not only applicable to exploration purposes but also essential for production, abandoned and environmental activities (e.g.
![introduction to artificial neural network by zurada pdf printer introduction to artificial neural network by zurada pdf printer](https://image.ceneostatic.pl/data/products/4778927/i-microsoft-autoroute-euro-eng-box-689-01039.jpg)
![introduction to artificial neural network by zurada pdf printer introduction to artificial neural network by zurada pdf printer](https://demo.fdocuments.in/img/378x509/reader018/reader/2020010703/54774f185906b576068b464a/r-1.jpg)
Compressional wave velocity, when used with shear wave velocity ( V s), creates an important parameter providing valuable information in seismic analysis, lithologic identification (Tatham 1982, Wilkens et al 1984), and pore fluid and pore pressure information (Duffaut and Landrø 2007, Rojas 2008). Since carbonate rocks are considered to be major parts of the world's oil and gas reservoirs, more research is required on the assessment of their physical characteristics. The result showed that an ANN outperforms MLRs and was found to be more robust and reliable.Ĭompressional wave velocity, artificial neural network, regression analysis, carbonate reservoirs Introduction The efficiency of the employed approach, quantified in terms of the mean squared error correlation coefficient ( R-square), and prediction efficiency error, is evaluated through simulation and the results are presented. A total of 2156 data points from a giant Middle Eastern carbonate reservoir, derived from a conventional wire line and a dipole sonic imager log were used in this study. The obtained results are compared to those of multiple linear regression (MLR) models. Therefore, an attempt has been made to develop a prediction model for V p as a function of some conventional well logs by using an artificial neural network (ANN). Therefore, formulating a prediction tool that can accurately estimate the lacking log data, such as V p, is of prime importance. Due to the different nature and behaviour of the influencing parameters, more complex nonlinearity exists for V p modelling purposes. As vital records for the upstream petroleum industry, compressional-wave ( V p) data provide important information for reservoir exploration and development activities.