Porosity and permeability prediction from wireline logs using artificial neural networks: a North Sea case study

Estimations of porosity and permeability from well logs are important yet d ifficult tasks encountered in geophysical formation evaluation and reservoi r engineering. Motivated by recent results of artificial neural network (AN N) modelling offshore eastern Canada, we have developed neural nets for con verting well logs in the North Sea to porosity and permeability. We use two separate back-propagation ANNs (BP-ANNs) to model porosity and permeabilit y. The porosity ANN is a simple three-layer network using sonic, density an d resistivity logs for input. The permeability ANN is slightly more complex with four inputs (density, gamma ray, neutron porosity and sonic) and more neurons in the hidden layer to account for the increased complexity in the relationships. The networks, initially developed for basin-scale problems, perform sufficiently accurately to meet normal requirements in reservoir e ngineering when applied to Jurassic reservoirs in the Viking Graben area. T he mean difference between the predicted porosity and helium porosity from core plugs is less than 0.01 fractional units. For the permeability network a mean difference of approximately 400 mD is mainly due to minor core-log depth mismatch in the heterogeneous parts of the reservoir and lack of adeq uate overburden corrections to the core permeability. A major advantage is that no a priori knowledge of the rock material and pore fluids is required . Real-time conversion based on measurements while drilling (MWD) is thus a n obvious application.