Technology for predictive natural disaster response

1. A method for predictive natural disaster response, comprising:

determining, by a server, at least one affected location, the affected location predicted to be affected by a natural disaster;

determining, by the server, whether the type of natural disaster requires relocation of an animal population at the affected location;

in response to determining that the relocation is not required:

generating, by the server, a demands prediction for products and services at the affected location using a set of machine learning models, wherein parameters input into the set of machine learning models comprise the population data for the animal population and a human population at the affected location, location data for the affected location, and consumption data for the animal population and the human population at the affected location;

generating, by the server, a supply prediction for the products and the services at the affected location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the population data for the animal population and the human population at the affected location, the location data for the affected location, and yield data for the animal population at the affected location;

generating, by the server, a supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the demands predication and the supply prediction; and

providing access to the supply plan by an interface over a computer network.

2. The method of claim 1 , further comprising:

in response to determining that the relocation is required:

generating, by the server, a rehabilitation needs prediction for the relocation using the set of machine learning models, wherein parameters input into the set of machine learning models comprise population data for the animal population at the affected location;

determining, by the server, at least one optimal location for the relocation from a plurality of candidate locations, using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the rehabilitation needs prediction and candidate location data for each of the plurality of candidate locations; and

generating, by the server using the set of machine learning models, a relocation plan to relocate the animal population from the affected location to the at least one optimal location.

3. The method of claim 1 , wherein after relocation of the animal population to the optimal location, the method further comprising:

updating the population data, the consumption data, and the yield data for the animal population at the optimal location;

generating, by the server, an updated demands prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated consumption data for the animal population;

generating, by the server, an updated supply prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated yield data for the animal population at the optimal location; and

generating, by the server, the supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated demands predication and the updated supply prediction.

4. The method of claim 1 , further comprising:

retrieving, by the server, the parameters input into the set of machine learning models from data stored in a blockchain.

5. The method of claim 1 , wherein the determining of the at least one optimal location and the generating of the relocation plan comprise:

determining, by the server, a plurality of optimal locations for the relocation from the plurality of candidate locations using the set of machine learning models;

dividing, by the server, the animal population into groups; and

generating, by the server, the relocation plan using the set of machine learning models to relocate each group of the animal population to a different optimal location of the plurality of optimal locations.

6. The method of claim 1 , wherein the generating of the supply prediction and the generating of the supply plan comprise:

predicting, by the server using the set of machine learning models, that another location will have an excess supply of the products or the services; and

generating, by the server, the supply plan using the set of machine learning models, wherein the supply plan includes movement of the excess supply of the products or the services from the other location to the affected location.

7. The method of claim 1 , wherein the set of machine learning models are configured with multiple decision trees and configured to use a random forest ensemble machine learning technique.

8. A computer program product for predictive natural disaster response, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer system, to cause the computer system to:

determine at least one affected location, the affected location predicted to be affected by a natural disaster;

determine whether the type of natural disaster requires relocation of an animal population at the affected location;

in response to determining that the relocation is not required:

generating, by the server, a demands prediction for products and services at the affected location using a set of machine learning models, wherein parameters input into the set of machine learning models comprise the population data for the animal population and a human population at the affected location, location data for the affected location, and consumption data for the animal population and the human population at the affected location;

generating, by the server, a supply prediction for the products and the services at the affected location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the population data for the animal population and the human population at the affected location, the location data for the affected location, and yield data for the animal population at the affected location;

generating, by the server, a supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the demands predication and the supply prediction; and

providing access to the supply plan by an interface over a computer network.

9. The computer program product of claim 8 , wherein the computer system is further caused to:

in response to determining that the relocation is required:

generating, by the server, a rehabilitation needs prediction for the relocation using the set of machine learning models, wherein parameters input into the set of machine learning models comprise population data for the animal population at the affected location;

determining, by the server, at least one optimal location for the relocation from a plurality of candidate locations, using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the rehabilitation needs prediction and candidate location data for each of the plurality of candidate locations; and

generating, by the server using the set of machine learning models, a relocation plan to relocate the animal population from the affected location to the at least one optimal location.

10. The computer program product of claim 8 , wherein after relocation of the animal population to the optimal location, the computer system is further caused to:

update the population data, the consumption data, and the yield data for the animal population at the optimal location;

generate an updated demands prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated consumption data for the animal population;

generate an updated supply prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated yield data for the animal population at the optimal location; and

generate the supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated demands predication and the updated supply prediction.

11. The computer program product of claim 8 , wherein the computer system is further caused to:

retrieve the parameters input into the set of machine learning models from data stored in a blockchain.

12. The computer program product of claim 8 , wherein in determining the at least one optimal location and in the generating of the relocation plan, the computer system is further caused to:

determine a plurality of optimal locations for the relocation from the plurality of candidate locations using the set of machine learning models;

divide the animal population into groups; and

generate the relocation plan using the set of machine learning models to relocate each group of the animal population to a different optimal location of the plurality of optimal locations.

13. The computer program product of claim 8 , wherein in the generating of the supply prediction and in the generating of the supply plan, the computer system is further caused to:

predict, using the set of machine learning models, that another location will have an excess supply of the products or the services; and

generate the supply plan using the set of machine learning models, wherein the supply plan includes movement of the excess supply of the products or the services from the other location to the affected location.

14. The computer program product of claim 8 , wherein the set of machine learning models are configured with multiple decision trees and configured to use a random forest ensemble machine learning technique.

15. A system comprising:

a processor; and

a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the processor, to cause the processor to:

determine at least one affected location, the affected location predicted to be affected by a natural disaster;

determine whether the type of natural disaster requires relocation of an animal population at the affected location;

in response to determining that the relocation is not required:

generating, by the server, a demands prediction for products and services at the affected location using a set of machine learning models, wherein parameters input into the set of machine learning models comprise the population data for the animal population and a human population at the affected location, location data for the affected location, and consumption data for the animal population and the human population at the affected location;

generating, by the server, a supply prediction for the products and the services at the affected location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the population data for the animal population and the human population at the affected location, the location data for the affected location, and yield data for the animal population at the affected location;

generating, by the server, a supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the demands predication and the supply prediction; and

providing access to the supply plan by an interface over a computer network.

16. The system of claim 15 , wherein the processor is further caused to:

in response to determining that the relocation is required:

generating, by the server, a rehabilitation needs prediction for the relocation using the set of machine learning models, wherein parameters input into the set of machine learning models comprise population data for the animal population at the affected location;

determining, by the server, at least one optimal location for the relocation from a plurality of candidate locations, using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the rehabilitation needs prediction and candidate location data for each of the plurality of candidate locations; and

generating, by the server using the set of machine learning models, a relocation plan to relocate the animal population from the affected location to the at least one optimal location.

17. The system of claim 15 , wherein after relocation of the animal population to the optimal location, the processor is further caused to:

update the population data, the consumption data, and the yield data for the animal population at the optimal location;

generate an updated demands prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated consumption data for the animal population;

generate an updated supply prediction for the products and the services at the optimal location using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated population data and the updated yield data for the animal population at the optimal location; and

generate the supply plan using the set of machine learning models, wherein the parameters input into the set of machine learning models comprise the updated demands predication and the updated supply prediction.

18. The system of claim 15 , wherein the processor is further caused to:

retrieve the parameters input into the set of machine learning models from data stored in a blockchain.

19. The system of claim 15 , wherein in determining the at least one optimal location and in the generating of the relocation plan, the processor is further caused to:

determine a plurality of optimal locations for the relocation from the plurality of candidate locations using the set of machine learning models;

divide the animal population into groups; and

generate the relocation plan using the set of machine learning models to relocate each group of the animal population to a different optimal location of the plurality of optimal locations.

20. The system of claim 15 , wherein in the generating of the supply prediction and in the generating of the supply plan, the processor is further caused to:

predict, using the set of machine learning models, that another location will have an excess supply of the products or the services; and

generate the supply plan using the set of machine learning models, wherein the supply plan includes movement of the excess supply of the products or the services from the other location to the affected location.