A Comparative Study between a Pseudo-Forward Equation (PFE) and Intelligence Methods for the Characterization of the North Sea Reservoir

This paper presents a comparative study between three versions of adaptive neuro-fuzzy inference system (ANFIS) algorithms and a pseudo-forward equation (PFE) to characterize the North Sea reservoir (F3 block) based on seismic data. According to the statistical studies, four attributes (energy, envelope, spectral decomposition and similarity) are known to be useful as fundamental attributes in porosity estimation. Different ANFIS models were constructed using three clustering methods of grid partitioning (GP), subtractive clustering method (SCM) and fuzzy c-means clustering (FCM). An experimental equation, called PFE and based on similarity attributes, was also proposed to estimate porosity values of the reservoir. When the validation set derived from training wells was used, the R-square coefficient between two variables (actual and predicted values) was obtained as 0.7935 and 0.7404 for the ANFIS algorithm and the PFE model, respectively. But when the testing set derived from testing wells was used, the same coefficients decreased to 0.252 and 0.5133 for the ANFIS algorithm and the PFE model, respectively. According to these results, and the geological characteristics observed in the F3 block, it seems that the ANFIS algorithms cannot estimate the porosity acceptably. By contrast, in the outputs of PFE, the ability to detect geological structures such as faults (gas chimney), folds (salt dome), and bright spots, alongside the porosity estimation of sandstone reservoirs, could help in determining the drilling target locations. Finally, this work proposes that the developed PFE could be a good technique for characterizing the reservoir of the F3 block.

Keywords:

ANFIS , clustering algorithms , experimental equation , porosity , seismic attributes