Communication site potential outage causing event impact prediction

1. A method, comprising:

executing, on a processor of a computing device, instructions that cause the computing device to perform operations, the operations comprising:

receiving first site features associated with a first communication site;

receiving second site features associated with a second communication site;

receiving event features associated with a potential outage-causing natural event;

employing a classifying engine to generate a first impact metric indicating an effect on the first communication site from the potential outage-causing natural event based on the first site features and the event features; and

employing the classifying engine to generate a second impact metric indicating an effect on the second communication site from the potential outage-causing natural event based on the second site features and the event features.

2. The method of claim 1 , wherein the operations comprise:

linking a communication site data store, a site outage data store, and an event data store based on a location field to generate a linked event impact data store; and

training the classifying engine using the linked event impact data store.

3. The method of claim 2 , wherein the operations comprise:

determining an actual effect of the potential outage-causing natural event on the first communication site; and

after training the classifying engine, retraining the classifying engine based on the potential outage-causing natural event and the actual effect.

4. The method of claim 2 , wherein:

the location field comprises a latitude field and a longitude field.

5. The method of claim 1 , wherein:

the first site features comprise at least one of site location, altitude, support structure height, support structure type, technology type, or site age.

6. The method of claim 1 , wherein:

the event features comprise at least one of event type or event location.

7. The method of claim 1 , wherein:

the potential outage-causing natural event comprises a predicted potential outage-causing event.

8. The method of claim 1 , wherein:

the potential outage-causing natural event comprises at least one of a flood, a hurricane, a tornado, a volcanic eruption, an earthquake, a tsunami, a storm, a geologic process or a fire.

9. A computing device, comprising:

a processor; and

memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:

receiving first candidate site features associated with a communication site;

receiving second candidate site features associated with the communication site;

receiving first event features associated with a first potential outage-causing event;

employing a classifying engine to generate a first impact metric indicating an effect on the communication site from the first potential outage-causing event for the first candidate site features based on the first candidate site features and the first event features; and

employing the classifying engine to generate a second impact metric indicating an effect on the communication site from the first potential outage-causing event for the second candidate site features based on the second candidate site features and the first event features.

10. The computing device of claim 9 , wherein:

the first candidate site features comprise a first support structure field; and

the second candidate site features comprise a second support structure field different than the first support structure field.

11. The computing device of claim 10 , wherein:

the first support structure field comprises at least one of a first support structure height or a first support structure type.

12. The computing device of claim 9 , wherein the operations comprise:

generating a recommendation selecting one of the first candidate site features or the second candidate site features based on the first impact metric and the second impact metric.

13. The computing device of claim 9 , wherein:

the first potential outage-causing event comprises at least one of a first thunderstorm event, a first marginal risk event, a first slight risk event, a first enhanced risk event, a first moderate risk event, or a first high risk event.

14. The computing device of claim 9 , wherein the operations comprise:

receiving second event features associated with a second potential outage-causing event;

employing the classifying engine to generate a third impact metric indicating an effect on the communication site from the second potential outage-causing event for the first candidate site features based on the first candidate site features and the second event features;

generating a first risk profile for the first candidate site features based on the first impact metric and the third impact metric;

employing the classifying engine to generate a fourth impact metric indicating an effect on the communication site from the second potential outage-causing event for the second candidate site features based on the second candidate site features and the second event features; and

generating a second risk profile for the second candidate site features based on the second impact metric and the fourth impact metric.

15. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:

receiving first site features associated with a first communication site;

receiving second site features associated with a second communication site;

receiving event features associated with a potential outage-causing event;

employing a classifying engine to generate a first impact metric indicating an effect on the first communication site from the potential outage-causing event based on the first site features and the event features;

employing the classifying engine to generate a second impact metric indicating an effect on the second communication site from the potential outage-causing event based on the second site features and the event features; and

generating a map indicating a first location of the first communication site overlaid with a first indicator corresponding to the first impact metric and indicating a second location of the second communication site overlaid with a second indicator corresponding to the second impact metric.

16. The non-transitory machine readable medium of claim 15 , wherein:

the first site features comprise at least one of site location, altitude, support structure height, support structure type, technology type, or site age.

17. The non-transitory machine readable medium of claim 15 , wherein:

the event features comprise at least one of event type or event location.

18. The non-transitory machine readable medium of claim 15 , wherein:

the potential outage-causing event comprises a predicted potential outage-causing event.

19. The non-transitory machine readable medium of claim 15 , wherein:

the potential outage-causing event comprises at least one of a thunderstorm event, a marginal risk event, a slight risk event, an enhanced risk event, a moderate risk event, or a high risk event.

20. The non-transitory machine readable medium of claim 15 , wherein the operations comprise:

receiving third site features associated with a third communication site; and

responsive to determining a third location of the third communication site does not correspond to an event location associated with the potential outage-causing event, indicating on the map the third location of the third communication site overlaid with a third indicator indicating an unaffected status.