Field operations system with filter

1. A method comprising:

accessing a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;

generating a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;

receiving operation data from the equipment responsive to controlled operation in the environment by a controller;

generating an internal state vector in the latent space using the operation data and the trained deep neural network;

comparing at least the internal state vector to at least the base internal state vector; and

based on the comparing, calibrating the controller for additional controlled operation in the environment.

2. The method of claim 1 further comprising, based on the comparing, controlling at least one piece of the equipment.

3. The method of claim 1 further comprising rendering a graphical representation of the internal state vector and the base internal state vector to a display.

4. The method of claim 3 wherein the rendering is performed responsive to generating the internal state vector using the operation data.

5. The method of claim 1 wherein the functions comprise transfer functions that associate the internal state vector at a time to a prior internal state vector and an operation vector and wherein the functions comprise a measurement function that associates a measurement vector with the internal state vector.

6. The method of claim 1 wherein the comparing at least the internal state vector to at least the base internal state vector comprises comparing in the latent space.

7. The method of claim 1 wherein the pre-defined operational procedure comprises a series of proscribed actions.

8. The method of claim 1 wherein the comparing at least the internal state vector to at least the base internal state vector comprises utilizing a score function.

9. The method of claim 1 wherein internal states of the internal state vector are represented as points in a state space.

10. The method of claim 9 wherein a distance between two sequential points in the state space represents a temporal process of the dynamic system that transitions the dynamic system from a first one of the points to the second one of the points.

11. The method of claim 10 comprising comparing the temporal process to a process of the pre-defined operational procedure.

12. The method of claim 1 wherein the equipment comprises well construction equipment.

13. The method of claim 1 wherein the environment comprises a formation in the Earth.

14. The method of claim 1 wherein the deep neural network is trained using time series data.

15. The method of claim 1 wherein the deep neural network is trained using multi-channel time series data.

16. A system comprising:

a processor;

memory accessible by the processor;

processor-executable instructions stored in the memory and executable to instruct the system to:

access a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;

generate a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;

receive operation data from the equipment responsive to controlled operation in the environment by a controller;

generate an internal state vector in the latent space using the operation data and the trained deep neural network;

perform a comparison at least the internal state vector to at least the base internal state vector; and

based on the comparison, calibrate the controller for additional controlled operation in the environment.

17. The system of claim 16 wherein the processor-executable instructions comprise instructions to, based on the comparison, instruct the system to control at least one piece of the equipment.

18. One or more non-transitory computer-readable storage media comprising processor-executable instructions to instruct a computing system to:

access a trained deep neural network wherein the trained deep neural network represents functions of a non-linear Kalman filter that represents a dynamic system of equipment and environment via an internal state vector of the dynamic system, wherein the deep neural network comprises a convolution neural network layer that represents a first one of the functions and a long short-term memory layer that represents second one of the functions;

generate a base internal state vector in a latent space, that corresponds to a pre-defined operational procedure, using the trained deep neural network;

receive operation data from the equipment responsive to controlled operation in the environment by a controller;

generate an internal state vector in the latent space using the operation data and the trained deep neural network;

perform a comparison at least the internal state vector to at least the base internal state vector; and

based on the comparison, calibrate the controller for additional controlled operation in the environment.

19. The one or more non-transitory computer-readable storage media of claim 18 wherein the processor-executable instructions comprise instructions to, based on the comparison, instruct the computing system to control at least one piece of the equipment.