Field equipment data system
A method can include receiving a request for field equipment data; responsive to the request, automatically processing the field equipment data using a trained machine learning model to generate a quality score for the field equipment data; and outputting the quality score.
1. A method comprising:
receiving, from a framework, a request for field equipment data obtained from field equipment at a reservoir;
automatically identifying, using a machine learning model, data types of the field equipment data;
automatically converting, by the machine learning model, the data types to a data structure used by the framework in response to the machine learning model determining that the data types are in a different format from the data structure used by the framework;
generating, by the machine learning model, a quality metric in response to performing a quality assessment of converting the data types to the data structure used by the framework;
providing the field equipment data in the data structure used by the framework and the quality metric; and
performing, in response to the quality metric exceeding a threshold, a simulation on the field equipment data.
2. The method of claim 1 , wherein the machine learning model performs dimensionality reduction on the field equipment data and an identification of spatial regions in the field equipment data wherein each of the spatial regions corresponds to one of the data types.
3. The method of claim 2 , wherein performing dimensionality reduction comprises performing principal component analysis (PCA).
4. The method of claim 2 , further comprising comparing the spatial regions for the field equipment data to defined spatial regions.
5. The method of claim 1 , wherein the machine learning model compares the data types to the data structure used by the framework and automatically converts the data types in response to determining the data types are in a different format from the data structure.
6. The method of claim 1 , wherein the machine learning model identifies units of measurement of the field equipment data.
7. The method of claim 6 , further comprising, responsive to identification of the units of measurement, the machine learning model converting the units of measurement for at least a portion of the field equipment data into a unit of measurement used by the framework.
8. The method of claim 1 , wherein the machine learning model identifies a coordinate reference system of the field equipment data.
9. The method of claim 8 , wherein the machine learning model, responsive to identification of the coordinate reference system, converts the coordinate reference system for at least a portion of the field equipment data to a coordinate reference system used by the framework.
10. The method of claim 1 , further comprising training the machine learning model.
11. The method of claim 10 , wherein the training comprises using supervised machine learning processes.
12. The method of claim 10 , wherein the training comprises using unsupervised machine learning processes.
13. The method of claim 12 , wherein the unsupervised machine learning processes use at least a portion of the field equipment data for the training.
14. The method of claim 1 , further comprising training the machine learning model using supervised learning and case-based reasoning.
15. The method of claim 1 , wherein the machine learning model analyzes variable properties of field equipment data variables to identify the data types.
16. The method of claim 15 , wherein the variable properties form a hierarchy.
17. The method of claim 16 , wherein the hierarchy comprises parent and child relationships.
18. The method of claim 1 , wherein if the quality metric is below the threshold, data degradation occurred during the conversion, and the method further comprises:
providing feedback to the machine learning model on the conversion; and
updating the machine learning model using the feedback.
19. A system comprising:
a processor;
memory accessible to the processor; and
processor-executable instructions stored in the memory to instruct the system to:
receive, from a framework, a request for field equipment data obtained from field equipment at a reservoir;
automatically identify, using a machine learning model, data types of the field equipment data;
automatically convert, by the machine learning model, the data types to a data structure used by the framework in response to the machine learning model determining that the data types are in a different format from the data structure used by the framework;
generate, by the machine learning model, a quality metric in response to performing a quality assessment of converting the data types to the data structure used by the framework;
provide the field equipment data in the data structure used by the framework and the quality metric; and
perform, in response to the quality metric exceeding a threshold, a simulation on the field equipment data.
20. One or more computer-readable storage media comprising processor-executable instructions to instruct a computing system to:
receive, from a framework, a request for field equipment data obtained from field equipment at a reservoir;
automatically identify, using a machine learning model, data types of the field equipment data;
automatically convert, by the machine learning model, the data types to a data structure used by the framework in response to the machine learning model determining that the data types are in a different format from the data structure used by the framework;
generate, by the machine learning model, a quality metric in response to performing a quality assessment of converting the data types to the data structure used by the framework;
provide the field equipment data in the data structure used by the framework and the quality metric; and
perform, in response to the quality metric exceeding a threshold, a simulation on the field equipment data.