System and method for damage assessment and restoration

1. A system for damage assessment and restoration, the system comprising:

an electronic processor configured to

receive weather data for an area of interest, wherein the weather data includes a weather observation for a weather event,

determine a first damage prediction for the area of interest using a damage prediction model developed with machine learning using training data, the training data including historical weather data for the area of interest and associated damage,

determine a restoration time estimate based on the first damage prediction for the area of interest based on different resource allocations,

determine a feasible range of an availability of resources and determine the restoration time estimate further based on the feasible range of the availability of resources, and

transmit a damage assessment report for display on a user device, wherein the damage assessment report includes the restoration time estimate.

2. The system of claim 1 , wherein the electronic processor is configured to access additional data for the area of interest and determine the first damage prediction for the area of interest based on the additional data for the area of interest, wherein the additional data includes at least one selected from a group consisting of environmental data and infrastructural data.

3. The system of claim 1 , wherein the electronic processor is configured to determine the first damage prediction for the area of interest by dividing the area of interest into a plurality of sub-areas, and determining a plurality of damage predictions, wherein each of the plurality of damage predictions is associated with each of the plurality of sub-areas of the area of interest.

4. The system of claim 1 , wherein the electronic processor is configured to determine the first damage prediction for the area of interest by determining a plurality of damage predictions, wherein each of the plurality of damage predictions is associated with an infrastructure asset of the area of interest.

5. The system of claim 1 , wherein the electronic processor is configured to determine the restoration time estimate using a restoration time model developed using machine learning.

6. The system of claim 1 , wherein the electronic processor is further configured to determine a logistical material estimate, the logistical material estimate including at least one selected from a group consisting of a type of material to repair damage to the area of interest, an amount of material to repair damage to the area of interest, and equipment to repair damage to the area of interest.

7. The system of claim 1 , wherein the damage assessment report includes at least one selected from a group consisting of a logistical material estimate, an availability of resources, the first damage prediction for the area of interest, a second damage prediction associated with an infrastructure asset of the area of interest, a third damage prediction associated with a sub-area of the area of interest, and an uncertainty indication associated with the restoration time estimate.

8. The system of claim 1 , wherein the electronic processor is further configured to receive actual damage data, wherein the actual damage data includes an operational status communicated by an infrastructure asset in the area of interest.

9. The system of claim 8 , wherein the electronic processor is further configured to determine a new restoration time estimate based on the actual damage data for the area of interest and transmit a subsequent damage assessment report for display on the user device, wherein the subsequent damage assessment report includes the new restoration time estimate.

10. The system of claim 8 , wherein the electronic processor is configured to update the damage prediction model based on the actual damage data.

11. The system of claim 1 , wherein the electronic processor is further configured to automatically prioritize available resources and manage allocation of the available resources for the area of interest based on at least one selected from the group consisting of the first damage prediction and the restoration time estimate.

12. A method for damage assessment and restoration, the method comprising:

receiving, with an electronic processor, weather data for an area of interest, wherein the weather data includes a weather observation for a weather event;

determining, with the electronic processor, a damage prediction for the area of interest using a damage prediction model developed with machine learning;

determining, with the electronic processor, a restoration time estimate for the area of interest using a restoration time model developed with machine learning, the restoration time estimate based on the damage prediction for the area of interest and different resource allocations;

determining, with the electronic processor, a feasible range of an availability of resources and determining the restoration time estimate further based on the feasible range of the availability of resources, and

transmitting, with the electronic processor, a damage assessment report for display on a user device, wherein the damage assessment report includes the restoration time estimate.

13. The method of claim 12 , wherein determining the damage prediction for the area of interest includes determining a damage prediction representing a damage occurrence probability distribution that describes a probability of different amounts of damage.

14. The method of claim 12 , further comprising:

developing the restoration time model with machine learning using training data, the training data including historical damage prediction data for an area of interest and associated historical restoration time data.

15. The method of claim 12 , wherein determining the damage prediction for the area of interest includes

accessing environmental data associated with the area of interest;

accessing infrastructural data associated with the area of interest; and

determining the damage prediction based on the environmental data and the infrastructural data.

16. A non-transitory, computer-readable medium including instructions that, when executed by an electronic processor, cause the electronic processor to execute a set of functions, the set of functions comprising:

receiving weather data for an area of interest, wherein the weather data includes a weather observation for a weather event;

determining a damage prediction for the area of interest using a damage prediction model developed with machine learning using training data, the training data including historical weather data for the area of interest and associated damage;

determining a restoration time estimate based on the damage prediction for the area of interest and different resource allocations;

determining a feasible range of an availability of resources and determining the restoration time estimate further based on the feasible range of the availability of resources,

transmitting a damage assessment report for display on a user device, wherein the damage assessment report includes the restoration time estimate;

receiving actual damage data for the area of interest;

determining a new restoration time estimate based on the actual damage data for the area of interest; and

transmitting a subsequent damage assessment report for display on the user device, wherein the subsequent damage assessment report includes the new restoration time estimate.

17. The computer-readable medium of claim 16 , wherein the set of functions further includes:

updating the damage prediction model based on the actual damage data.

18. The computer-readable medium of claim 16 , wherein determining the damage prediction for the area of interest includes determining a damage prediction representing a damage occurrence probability distribution that describes a probability of different amounts of damage.

19. The computer-readable medium of claim 16 , wherein receiving the actual damage data for the area of interest includes receiving an onsite damage assessment for the area of interest.