development of an artificial neural network model to calculate static young’s modulus based on a log-derived data base

Static young’s modulus is a measure of reservoir rock stiffness and is best determined by experimental studies on cores. however, the experimental procedures are demanding with considerable cost. on the other hand, a dynamic young’s modulus can easily be estimated from readily available petrophysical data. the static young’s modulus can easily be obtained from the dynamic counterpart by empirical relationships. this research attempts to use ai techniques to predict static young’s modulus. two thousand three hundred fifty data sets were collected from several wells in the middle east with sandstone and limestone lithology and used to build an ai model. each data set contains static young’s modulus as a function of the bulk density, shear wave arrival time, and compressional wave arrival time. an artificial neural network (ann) model was developed to predict the static young’s modulus with high accuracy of r² = 0.999 and aare of 0.028%. the proposed model was validated with measured reservoir rock data and was compared with four different correlations. the results showed that the model provided the highest coefficient of determination (r²) and the lowest standard deviation.