Porosity estimation by neural networks for CO2 storage in Otway site

Abstract Dynamic simulation of CO 2 migration requires a variety modeling parameters fed by geomechanical models. The confidence these material groups such as porosity and permeability is crucial in achieving successful simulations. Based on the geophysical parameters, we estimated distributions Paaratte Formation Otway site, one storage project Australia. Considering nonlinear relations between logs seismic data, applied neural network scheme that addresses value across whole domain. With only monitoring well two injection wells at data are used to restore spatial absence porosity. technique was conducted based integration volume inversion acoustic impedance. results indicated correlation tie 75% recorded 87% average. Further, time slice maps depth interval demonstrated plume developed formation site.