| CPC G06F 16/29 (2019.01) [G06F 16/24578 (2019.01); G06F 16/248 (2019.01); G06N 20/00 (2019.01)] | 20 Claims |
|
1. A method comprising:
receiving input data characterizing a geologic environment, wherein the input data comprises one or more surface-level features indicative of one or more subterranean formations;
responsive to receipt of the input data characterizing the geologic environment, utilizing a trained machine learning model to identify a number of geologic environments that comprise corresponding data similar to the input data and stored in at least one database;
analyzing one or more sets of historical data representative of the number of geologic environments to determine a likelihood of a particular subterranean formation being associated with the one or more surface-level features of the geologic environment;
outputting a result based at least in part on the analyzing, wherein the result is indicative of the particular subterranean formation associated with the one or more surface-level features of the geologic environment;
utilizing the trained machine learning model to perform a geochemical simulation to simulate an evolution of a hydrocarbon formation and composition to obtain simulation results based at least in part on the particular subterranean formation associated with the result and the one or more sets of historical data;
utilizing the simulation results as feedback to retrain the machine learning model, wherein the trained machine learning model includes the simulation results in the input data to the trained machine learning model;
generating a development plan based at least in part on the result, wherein the development plan is associated with the geologic environment for operations related to production of hydrocarbon fluid; and
controlling equipment at a wellsite based on the development plan.
|