Prediction of reservoir fluid properties from mud-gas data

摘要

A method of creating a model of a subterranean reservoir for predicting property of a fluid in a reservoir comprising selecting a subset of available reservoir samples based on a degree of biodegradation of the samples, generating an input data set 102 comprising input mud-gas data and fluid property data, and generating a model using a machine learning algorithm or correlation. The model can be used to predict the fluid properties for other sample locations based on mud-gas data for that location. The application of this technique allows a continuous log of the selected property to be generated using mud-gas data collected during the well drilling process.