Systems and methods for probabilistic well depth prognosis

1. A method for drilling a well into a subsurface formation, the method comprising:

performing a seismic survey of the subsurface formation to generate seismic data;

receiving data representing a plurality of depth maps for a subsurface region, each depth map of the plurality of depth maps being generated from the seismic data acquired in the seismic survey of the subsurface region;

determining, for one or more depth maps of the plurality, a respective weight value;

generating data representing a combination of the plurality of depth maps based on the respective weight values of the one or more depth maps of the plurality;

generating a cumulative distribution function (CDF) for a particular location in the subsurface region based on the data representing a combination of the plurality of depth maps;

determining, for the particular location in the subsurface region based on the CDF for that particular location, a probability value representing a depth at which a geological layer occurs in the subsurface region at the particular location; and

drilling the well into the subsurface formation at the particular location to a target depth based on the probability value representing a depth at which a geological layer occurs.

2. The method of claim 1 , further comprising generating, based on the CDF for the particular location, a visualization showing, for one or more depth values, an associated probability value.

3. The method of claim 1 , wherein each depth map of the plurality of depth maps is generated based on a respective combination of seismic survey, seismic survey interpretation in a time domain, velocity model, and depth conversion at a unique location in the subsurface region.

4. The method of claim 1 , wherein determining the respective weight values comprises:

setting a same weight value for each depth map of the plurality.

5. The method of claim 1 , wherein determining the respective weight values comprises:

selecting different weight values for at least two respective depth maps of the plurality.

6. The method of claim 1 , wherein determining the respective weight values comprises:

determining a value of a data quality metric of a seismic survey, interpretation, or velocity model that is used for generating a depth map of the plurality of depth maps; and

selecting a weight value based on the value of the data quality metric.

7. The method of claim 1 , wherein determining the respective weight values comprises:

training a machine learning model using data representing one or more labeled depth maps;

inputting the data representing a plurality of depth maps into the trained machine learning model; and

generating, by the trained machine learning model, a weight value for one or more of the depth maps.

8. The method of claim 1 , wherein generating data representing a combination of the plurality of depth maps comprises generating data including at least one of a mean, a standard deviation, or a statistical property of the plurality of depth maps.

9. The method of claim 1 , wherein the probability value representing the depth at which the geological layer occurs in the subsurface region at the particular location corresponds to an oil-water contact, a gas-oil contact, a gas-water contact, a CO 2 -water contact, or a halocline.

10. A data processing system for drilling a well into a subsurface formation, the data processing system comprising:

at least one processor; and

memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

performing a seismic survey of the subsurface formation;

receiving data representing a plurality of depth maps for a subsurface region, each depth map of the plurality of depth maps being generated from seismic data acquired in a seismic survey at a location in the subsurface region;

determining, for one or more depth maps of the plurality, a respective weight value;

generating data representing a combination of the plurality of depth maps based on the respective weight values of the one or more depth maps of the plurality;

generating a cumulative distribution function (CDF) for a particular location in the subsurface region based on the data representing a combination of the plurality of depth maps;

determining, for the particular location in the subsurface region based on the CDF for that particular location, a probability value representing a depth at which a geological layer occurs in the subsurface region at the particular location; and

drilling the well into the subsurface formation at the particular location to a target depth based on the probability value representing a depth at which a geological layer occurs.

11. The data processing system of claim 10 , the operations further comprising generating, based on the CDF for particular well location, a visualization showing, for one or more depth values, an associated probability value.

12. The data processing system of claim 10 , wherein each depth map of the plurality of depth maps is generated based on a respective combination of seismic survey, seismic survey interpretation in a time domain, velocity model, and depth conversion at a unique location in the subsurface region.

13. The data processing system of claim 10 , wherein determining the respective weight values comprises:

setting a same weight value for each depth map of the plurality.

14. The data processing system of claim 10 , wherein determining the respective weight values comprises:

selecting different weight values for at least two respective depth maps of the plurality.

15. The data processing system of claim 10 , wherein determining the respective weight values comprises:

determining a value of a data quality metric of a seismic survey, interpretation, or velocity model that is used for generating a depth map of the plurality of depth maps; and

selecting a weight value based on the value of the data quality metric.

16. The data processing system of claim 10 , wherein determining the respective weight values comprises:

training a machine learning model using data representing one or more labeled depth maps;

inputting the data representing a plurality of depth maps into the trained machine learning model; and

generating, by the trained machine learning model, a weight value for one or more of the depth maps.

17. The data processing system of claim 10 , wherein generating data representing a combination of the plurality of depth maps comprises generating data including at least one of a mean, a standard deviation, or a statistical property of the plurality of depth maps.

18. The data processing system of claim 10 , wherein the probability value representing the depth at which the geological layer occurs in the subsurface region at the particular location corresponds to an oil-water contact, a gas-oil contact, a gas-water contact, a CO 2 -water contact, or a halocline.

19. A method performed by a data processing system configured to generate probabilistic data for planning a well depth for subsurface exploration, the method comprising:

receiving data representing a plurality of depth maps for a subsurface region, each depth map of the plurality of depth maps being generated from seismic data acquired in a seismic survey at a location in the subsurface region;

determining, for one or more depth maps of the plurality, a respective weight value;

generating data representing a combination of the plurality of depth maps based on the respective weight values of the one or more depth maps of the plurality;

generating a cumulative distribution function (CDF) for a particular location in the subsurface region based on the data representing a combination of the plurality of depth maps; and

determining, for the particular location in the subsurface region based on the CDF for that particular location, a probability value representing a depth at which a geological layer occurs in the subsurface region at the particular location.

20. The method of claim 19 , wherein the probability value representing the depth at which the geological layer occurs in the subsurface region at the particular location corresponds to an oil-water contact, a gas-oil contact, a gas-water contact, a CO2-water contact, or a halocline.