Automated offset well analysis
A system and method that includes querying a database to obtain offset well data collected while drilling previously drilled wells. The system and method also include determining if at least one risk is identified with respect to a planned well based on the offset well data. The system and method additionally include generating a machine learning model based on the at least one risk that is identified based on the offset well data. The system and method further include predicting at least one drilling risk based on the machine learning model, wherein a drill plan that includes drilling parameters is adjusted based on the at least one predicted drilling risk.
1. A method, comprising:
querying a database to obtain offset well data collected while drilling previously drilled wells;
identifying at least one risk with respect to a planned well based on the offset well data;
generating a machine learning model that quantifies the at least one risk in the planned well based on the at least one risk that was identified based on the offset well data;
predicting at least one drilling risk based on the machine learning model, wherein a drill plan that includes drilling parameters is adjusted based on the at least one predicted drilling risk, and wherein predicting the at least one drilling risk based on the machine learning model includes completing reinforcement learning to combine probabilities with connected reasons to predict the at least one drilling risk; and
drilling the planned well using the drilling parameters after adjusting the drilling parameters based on the at least one predicted drilling risk.
2. The method of claim 1 , wherein the database stores risks and hazards that have been encountered while drilling the previously drilled wells.
3. The method of claim 1 , wherein determining if the at least one risk is identified includes transforming data measurements included within the offset well data into an actionable insight, wherein the offset well data includes at least one automatic risk inference.
4. The method of claim 3 , wherein generating the machine learning model comprises training the machine learning model to predict the drilling risks based on the at least one automatic risk inference.
5. The method of claim 1 , wherein completing the reinforcement learning comprises using a Bayesian Belief Network to combine the probabilities with the connected reasons to predict the at least one drilling risk.
6. The method of claim 1 , wherein predicting the at least one drilling risk based on the machine learning model includes predicting at least one of: a risk of differential sticking in the planned well, or a risk of solid-induced pack-off in the planned well.
7. The method of claim 1 , further including generating a visual representation of the at least one drilling risk that includes a value that represents a likelihood of the at least one drilling risk being realized while drilling the planned well.
8. A system comprising:
a processor;
memory accessible by the processor;
processor-executable instructions stored in the memory and executable to instruct the system to:
query a database to obtain offset well data collected while drilling previously drilled wells;
identify at least one risk with respect to a planned well based on the offset well data;
generate a machine learning model that quantifies the at least one risk in the planned well based on the at least one risk that was identified based on the offset well data;
predict at least one drilling risk based on the machine learning model, wherein a drill plan that includes drilling parameters is adjusted based on the at least one predicted drilling risk, and wherein the at least one drilling risk predicted based on the machine learning model is predicted at least in part by completing reinforcement learning to combine probabilities with connected reasons to predict the at least one drilling risk; and
generate a visual representation, in a graphical user interface configured to display data related to the drill plan, of the at least one drilling risk that includes a value that represents a likelihood of the at least one drilling risk being realized while drilling the planned well.
9. The system of claim 8 , wherein the database stores risks and hazards that have been encountered while drilling the previously drilled wells.
10. The system of claim 8 , wherein the instructions further instruct the system to transform data measurements included within the offset well data into an actionable insight, wherein the offset well data includes at least one automatic risk inference.
11. The system of claim 10 , wherein the instructions further instruct the system to train the machine learning model to predict the drilling risks based on the at least one automatic risk inference.
12. The system of claim 8 , wherein completing the reinforcement learning comprises using a Bayesian Belief Network to combine the probabilities with the connected reasons to predict the at least one drilling risk.
13. The system of claim 8 , wherein the instructions further instruct the system to predict at least one of:
a risk of differential sticking in the planned well or a risk of solid-induced pack-off in the planned well.
14. The system of claim 8 , wherein the instructions further instruct the system to drill the planned well using the drilling parameters after adjusting the drilling parameters based on the at least one predicted drilling risk.
15. The system of claim 8 , wherein the instructions further instruct the system to generate a visual representation of the at least one drilling risk that includes a value that represents a likelihood of the at least one drilling risk being realized while drilling the planned well.
16. A non-transitory computer-readable storage medium storing instructions that when executed by a computer, which includes a processor, perform a method, the method comprising:
querying a database to obtain offset well data collected while drilling previously drilled wells;
identifying at least one risk is identified with respect to a planned well based on the offset well data;
generating a machine learning model that quantifies the at least one risk in the planned well based on the at least one risk that was identified based on the offset well data;
predicting at least one drilling risk based on the machine learning model, wherein a drill plan that includes drilling parameters is adjusted based on the at least one predicted drilling risk, and wherein predicting the at least one drilling risk based on the machine learning model includes completing reinforcement learning to combine probabilities with connected reasons to predict the at least one drilling risk, and
adjusting a physical drilling operation in response to adjusting the drill plan based on the at least one predicted drilling risk.
17. The non-transitory computer-readable storage medium of claim 16 , wherein predicting the at least one drilling risk based on the machine learning model includes completing the reinforcement learning using a Bayesian Belief Network to combine the probabilities with the connected reasons to predict the at least one drilling risk.
18. The non-transitory computer-readable storage medium of claim 16 , wherein predicting the at least one drilling risk based on the machine learning model includes predicting at least one of: a risk of differential sticking in the planned well, or a risk of solid-induced pack-off in the planned well.