Systems and methods for smart production operations

1 . A method, comprising:

receiving a plurality of datasets from one or more devices in a resource extraction site,

the plurality of datasets including sensor data and/or operational data from the one or more devices, and

the one or more devices including a valve, manifold, and/or pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof;

selecting a respective machine learning model for each context identified in the plurality of datasets, wherein each dataset is associated with respective equipment of the resource extraction site;

determining an additional device to deploy at a recommended location in the resource extraction site and one or more operational parameters for the additional device using the respective machine learning model and the plurality of datasets, the additional device including at least one selected from a group consisting of a valve, a manifold, and a pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof;

deploying the additional device to the recommended location at the resource extraction site:

generating one or more commands for implementing the one or more operational parameters for the additional device; and

sending the one or more commands to the additional device to cause the additional device to operate according to the one or more operational parameters.

2 . The method of claim 1 , wherein selected machine learning models are trained using datasets associated with one or more additional devices in one or more resource extraction sites.

3 . The method of claim 1 , wherein the plurality of datasets comprises pressure data, temperature data, speed data, frequency data, operational data, position data, or any combination thereof.

4 . The method of claim 1 , wherein each machine learning model is trained to identify at least one relationship between at least one of the plurality of datasets and at least one of the one or more operational parameters for the additional device, wherein the at least one relationship corresponds to increased production in the resource extraction site.

5 . The method of claim 1 , wherein the one or more commands are configured to cause the one or more devices to actuate.

6 . The method of claim 1 , wherein the plurality of datasets is received via a communication protocol and the one or more commands is sent via the communication protocol.

7 . A system, comprising:

one or more devices in a resource extraction site, wherein the one or more devices is configured to acquire a plurality of datasets associated with the resource extraction site,

the plurality of datasets including sensor data and/or operational data from the one or more devices, and

the one or more devices including a valve, manifold, and/or pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof; and

a remote computing system configured to:

receive the plurality of datasets;

select a machine learning model for each context identified in the plurality of datasets, wherein each dataset is associated with one or more operations of the one or more devices based on the plurality of datasets;

determine an additional device to deploy at a recommended location in the resource extraction site and one or more operational parameters for the additional device based on a corresponding machine learning model and the plurality of datasets, the additional device including at least one selected from a group consisting of a valve, a manifold, and a pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof;

responsive to deployment of the additional device at the recommended location, generate one or more commands for implementing the one or more operational parameters for the additional device; and

send the one or more commands to the additional device to cause the additional device to operate according to the one or more operational parameters.

8 . The system of claim 7 , wherein the plurality of datasets comprises pressure data, temperature data, speed data, frequency data, operational data, position data, or any combination thereof.

9 . The system of claim 7 , wherein selected machine learning models are configured to identify at least one relationship between at least one of the plurality of datasets and at least one of the one or more operational parameters for the additional device, wherein the at least one relationship corresponds to increased production in the resource extraction site.

10 . The system of claim 7 , wherein the one or more devices are configured to inject one or more chemicals into one or more oil production wells.

11 . The system of claim 7 , wherein the one or more devices are configured to inject water into one or more water injector or one or more water disposal wells.

12 . The system of claim 7 , wherein the plurality of datasets is received via a communication protocol and the one or more commands are sent via the communication protocol.

13 . A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processing system to perform operations comprising:

receiving a plurality of datasets from one or more devices in a resource extraction site,

the plurality of datasets including sensor data and/or operational data from the one or more devices, and

the one or more devices including a valve, manifold, and/or pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof;

selecting a machine learning model for each data context identified in respective datasets of the plurality of datasets, wherein each machine learning model is associated with one or more operations of the one or more devices, wherein each machine learning model is trained using datasets associated with one or more additional devices in one or more resource extraction sites, and wherein multiple machine learning models are selected for respective portions of at least one dataset to model characteristics between the respective portions and operational characteristics of the one or more devices;

determining an additional device to deploy at a recommended location in the resource extraction site and one or more operational parameters for the additional device based on a selected machine learning model and the plurality of datasets, the additional device including at least one selected from a group consisting of a valve, a manifold, and a pump of chemical injection equipment, water flooding equipment, artificial lift equipment, liquid metering equipment, power generation equipment, or a combination thereof;

responsive to deployment of the additional device, generating one or more commands for implementing the one or more operational parameters for the additional device; and

sending the one or more commands to the additional device to cause the additional device to operate according to the one or more operational parameters.

14 . The non-transitory computer-readable medium of claim 13 , wherein the plurality of datasets comprises pressure data, temperature data, speed data, frequency data, operational data, position data, or any combination thereof.

15 . The non-transitory computer-readable medium of claim 13 , wherein each machine learning model is configured to identify at least one relationship between at least one of the plurality of datasets and at least one of the one or more operational parameters for the additional device, wherein the at least one relationship corresponds to increased production in the resource extraction site.

16 . The non-transitory computer-readable medium of claim 13 , wherein the plurality of datasets is received via a communication protocol and the one or more commands are sent via the communication protocol.

17 . The non-transitory computer-readable medium of claim 13 , wherein each data context is associated with at least one of flow rate, production, or emissions.