Prediction of reservoir parameters in gas hydrate sediments using artificial intelligence (AI): A case study in Krishna–Godavari basin (NGHP Exp-02)

Abstract

The estimation of accurate reservoir parameters is essential for conventional and non-conventional hydrocarbon prospects. An artificial neural network has been developed to predict the reservoir parameters (porosity and saturation of gas hydrates) in a silty-sand, sandy-silt and pelagic-poor clay reservoir at two neighbour wells using the petrophysical information at another well in the Krishna–Godavari basin. The well log data were acquired during the Expedition-02 of Indian National Gas Hydrates Program (NGHP Exp-02). The estimation of gas hydrate saturation using Archie’s equation may be erroneous, as it is valid for the quantification of conventional hydrocarbons in the clean sand reservoir. Since the study area is clay dominated, it is subjective to adjust Archie’s exponents so that it matches with the saturation, measured from the core data. To overcome this problem of estimating the reservoir parameters in such a scenario, first of all we have derived porosity from the density log data and estimated saturation by employing modified Archie’s equation to the resistivity log data at one well. In order to train the network, the log data at one well are taken as inputs and corresponding porosity and saturation are taken as outputs. The reservoir parameters are then predicted at two neighbour wells using the wireline log data as input in those two wells. The predicted porosity and saturation of gas hydrates are alike to the traditionally estimated porosity and saturation at the neighbour wells. The predicted porosity in the studied region varies between 33 and 76%, whereas the saturation of gas hydrates ranges between 3.39 and 86.92%. This shows that the designed network can be used to estimate the reservoir parameters directly from the well log data in the same reservoirs.