Data driven model for sonic well log prediction

Abstract

Near wellbore failure during the exploration of hydrocarbon reservoirs presents a serious concern to the oil and gas industry. To predict the probability of these undesirable phenomena, engineers study the mechanical rock properties of the formation such as Young's modulus, Bulk modulus, shear modulus and Poisson's ratio. Conventionally, these are measured indirectly using the established petro physical relationships from sonic wave velocities which can be obtained from sonic well logs. Unfortunately, reliable sonic well logs are not always available, due to poor borehole conditions (wash out), damaged tools and offset well data. Most offset well log data are not acquired with dipole sonic tools; they are acquired with a borehole compensated logging tool. This limits the application of acoustic measurements to estimate the mechanical rock properties.In this study, a three-layer feedforward multilayered perceptron artificial neural network model is presented. This model aims to estimate compressional wave transit time and shear wave transit time using real gamma ray and formation density logs. The validation of the model is confirmed by using an oil and gas offshore shaley sandstone reservoir located in West Africa. The results of the validation show that the model presented in this study can be used to determine the sanding potential of the formation without performing a compressive geoscientific analysis in the absence of sonic well logs. The developed model's effectiveness is tested by comparing the predicted results with results obtained from the measured well log. The paper provides a tool to give preliminary recommendations of the likelihood of the formation to produce sand. Implementation of the proposed model can serve as a cost-effective and reliable alternative for the oil and gas industry.