Estimation of petrophysical parameters using seismic inversion and neural network modeling in Upper Assam basin, India

Estimation of petrophysical parameters is an important issue of any reservoirs. Porosity, volume of shale and water saturation has been evaluated for reservoirs of Upper Assam basin, located in northeastern India from well log and seismic data. Absolute acoustic impedance (AAI) and relative acoustic impedance (RAI) are generated from model based inversion of 2-D post-stack seismic data. The top of geological formation, sand reservoirs, shale layers and discontinuities at faults are detected in RAI section under the study area. Tipam Sandstone (TS) and Barail Arenaceous Sandstone (BAS) are the main reservoirs, delineated from the logs of available wells and RAI section. Porosity section is obtained using porosity wavelet and porosity reflectivity from post-stack seismic data. Two multilayered feed forward neural network (MLFN) models are created with inputs: AAI, porosity, density and shear impedance and outputs: volume of shale and water saturation with single hidden layer. The estimated average porosity in TS and BAS reservoir varies from 30% to 36% and 18% to 30% respectively. The volume of shale and water saturation ranges from 10% to 30% and 20% to 60% in TS reservoir and 28% to 30% and 23% to 55% in BAS reservoir respectively.