Abstract: A method is disclosed for generating a machine learning model to predict a reservoir fluid property, such as gas-oil ratio or density, based on standard mud-gas and petrophysical data. It has been found that this model predicts these reservoir fluid properties with an accuracy that is close to that which can be achieved using advanced mud-gas data. This is advantageous, as than standard mud-gas data and petrophysical data is much more readily available than advanced mud-gas data.

Abstract: A microfluidic device includes a microfluidic substrate having a porous media channel, an oil inlet port in fluid communication with the porous media channel, a fluid inlet port in fluid communication with the porous media channel, and an outlet port in fluid communication with the porous media channel. The porous media channel has a plurality of dividers that provide the porous media channel with a network of fluid pathways. A method for assessing miscibility of an oil composition and a fluid includes flowing an aliquot of a fluid through a porous media channel to displace at least an oil composition from the porous media channel, and conducting an optical investigation of the porous media channel to assess the miscibility of the oil composition and the fluid at the test pressure and test temperature.