| CPC E21B 49/0875 (2020.05) [E21B 21/067 (2013.01); E21B 49/005 (2013.01); E21B 49/084 (2013.01); E21B 49/086 (2013.01); E21B 49/088 (2013.01); G01N 33/2823 (2013.01); E21B 2200/20 (2020.05); E21B 2200/22 (2020.05)] | 20 Claims |
|
1. A method comprising:
obtaining input data regarding at least one measured property, wherein the at least one measured property includes an amount of each of a predetermined plurality of hydrocarbons in a gas sample extracted from drilling fluid after the drilling fluid exits a wellbore, and wherein the wellbore penetrates a subterranean formation comprising a hydrocarbon resource; and
predicting an unknown characteristic of an investigated fluid property of the hydrocarbon resource utilizing:
the obtained input data; and
one or more predetermined models each built via statistical classification and regression analysis of a preexisting database containing a plurality of records, wherein each record comprises known characteristics of a plurality of fluid properties of a different one of a plurality of known reservoir fluids, wherein the plurality of fluid properties comprises the investigated fluid property and the at least one measured property, and wherein the investigated fluid property comprises at least one of a fluid type of the hydrocarbon resource, an amount of at least one additional hydrocarbon, a gas-oil ratio (GOR), or a stock tank oil (STO) density; and
determining a first unknown characteristic of the investigated fluid property comprises:
classifying the gas sample as one of a first predetermined clusters of a plurality of predetermined clusters by utilizing the obtained input data and a first predetermined classification model; and
determining the first unknown characteristic of the first investigated fluid property by utilizing the obtained input data and one of a first predetermined prediction models that is specific to the first predetermined cluster in which the gas sample is classified;
determining a second unknown characteristic of a second investigated fluid properly by:
classifying the gas sample as one of a second predetermined clusters of the plurality of predetermined clusters by utilizing the obtained input data and a second predetermined classification model; and
utilizing the obtained input data, the determined first unknown characteristic of the first investigated fluid property, and one of a second predetermined prediction models that is specific to the second predetermined cluster in which the gas sample is classified.
|