Natural disaster forecasting

• US 9,262,124 B2
• Filed: 11/21/2011
• Issued: 02/16/2016
• Est. Priority Date: 11/21/2011
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Mello, Ulisses Thibes, Real, Lucas Villa
• Primary Examiner(s): Shah, Kamini S
• Assistant Examiner(s): GUILL, RUSSELL L
• Application Number:
  US13/301,062
• Publication Number:
  US 20130132045A1
• Time in Patent Office: 1,548 Days
• Field of Search: 703/2, 703/6, 702/3
• US Class Current: 1/1
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 7/60 Methods or arrangements for performing computations using a digital non-denominational number representation, i.e. number representation without radix; Computing devices using combinations of denominational and non-denominational quantity representations , e.g. using difunction pulse trains, STEELE computers, phase computers conversion of digital data to or from non-denominational form H03M5/00, H03M7/00
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety

Abstract

A method, an apparatus and an article of manufacture for estimating risk of impact of a natural disaster on a populated area. The method includes using dynamic natural disaster modeling information to estimate a spatio-temporal distribution of a parameter of a potential natural disaster, wherein the modeling information is input to an instance of a weather forecast model which computes simulation results for natural disaster parameters for an area at a given time interval and the results produced on each time step within the time interval the estimate of the spatio-temporal distribution, and using static demographic data to estimate risk of impact of the parameter of the natural disaster on a populated area based on the estimated spatio-temporal distribution, wherein the demographic data is overlayed with the estimated spatio-temporal distribution via applying a weight to each populated area based on historical natural disaster incidents and related impact for each area.

Claims

1. A method for estimating risk of impact of a natural disaster on a populated area, wherein the method comprises:

estimating a spatio-temporal distribution of a parameter of a potential natural disaster based on a collection of dynamic natural disaster modeling information, wherein the collection of dynamic natural disaster modeling information comprises at least information derived from a global weather model and satellite data comprising at least rain quantity and soil moisture saturation for multiple populated areas, and wherein said estimating the spatio-temporal distribution comprises;

inputting the dynamic natural disaster modeling information to an instance of a weather forecast model to compute simulation results for multiple natural disaster parameters for an area at a given time interval; and

incorporating the simulation results produced on each time step within the given time interval into the estimate of the spatio-temporal distribution of a parameter of the potential natural disaster;

estimating risk of impact of the parameter of the potential natural disaster on the multiple populated areas based on (i) the estimated spatio-temporal distribution of the parameter and (ii) a collection of static demographic data comprising information pertaining at least to topography slope, soil type, vegetation, water bodies, land use, drainage networks, and population occupation for the multiple populated areas, wherein said estimating the risk of impact comprises;

overlaying the static demographic data with the estimated spatio-temporal distribution; and

applying a weight to each of the multiple populated areas based on (i) historical natural disaster incidents for each of the multiple populated areas and (ii) impact corresponding to said historical natural disaster incidents for each of the multiple populated areas;

using the estimated risk of impact of the parameter of the potential natural disaster on the multiple populated areas to generate multiple natural disaster management strategies for the multiple populated areas; and

generating at least one key performance indicator for assessing risk for each of the multiple natural disaster management strategies.

2. The method of claim 1, further comprising facilitating a user to select a desired one of the multiple disaster management strategies based on the at least one key performance indicator.

3. The method of claim 1, further comprising updating each of the multiple natural disaster management strategies as new temporal data is collected.

4. The method of claim 1, wherein the collection of dynamic natural disaster modeling information comprises an ensemble of models taking multiple realizations of at least one probable atmospheric parameter.

5. The method of claim 1, wherein the collection of dynamic natural disaster modeling information comprises data that varies in location and time.

6. The method of claim 1, wherein using the collection of static demographic data to estimate risk of impact of the parameter of the potential natural disaster on the multiple populated areas based on the estimated spatio-temporal distribution of the parameter comprises overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas.

7. The method of claim 6, wherein overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas comprises facilitating prioritization of an area with a higher probability of occurrence.

8. The method of claim 1, wherein the collection of dynamic natural disaster modeling information further comprises at least information derived from a government agency, a weather station and a developed analytical model.

9. The method of claim 1, further comprising:

providing a system, wherein the system comprises at least one distinct software module, each distinct software module being embodied on a tangible computer-readable recordable storage medium, and wherein the at least one distinct software module comprises a prediction engine model module and an analytical model module executing on a hardware processor.

10. An article of manufacture comprising a non-transitory computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computer to carry out a plurality of method steps comprising:

estimating a spatio-temporal distribution of a parameter of a potential natural disaster based on a collection of dynamic natural disaster modeling information, wherein the collection of dynamic natural disaster modeling information comprises at least information derived from a global weather model and satellite data, and wherein said estimating the spatio-temporal distribution comprises;

inputting the dynamic natural disaster modeling information to an instance of a weather forecast model to compute simulation results for multiple natural disaster parameters for an area at a given time interval; and

incorporating the simulation results produced on each time step within the given time interval into the estimate of the spatio-temporal distribution of a parameter of the potential natural disaster;

estimating risk of impact of the parameter of the potential natural disaster on multiple populated areas based on (i) the estimated spatio-temporal distribution of the parameter and (ii) a collection of static demographic data comprising information pertaining at least to topography, water bodies, and population occupation, wherein said estimating the risk of impact comprises;

overlaying the static demographic data with the estimated spatio-temporal distribution; and

applying a weight to each of the multiple populated areas based on (i) historical natural disaster incidents for each of the multiple populated areas and (ii) impact corresponding to said historical natural disaster incidents for each of the multiple populated areas;

using the estimated risk of impact of the parameter of the potential natural disaster on the multiple populated areas to generate multiple natural disaster management strategies for the multiple populated areas; and

generating at least one key performance indicator for assessing risk for each of the multiple natural disaster management strategies.

11. The article of manufacture of claim 10, wherein the computer readable instructions which, when implemented, further cause a computer to carry out a method step comprising updating each of the multiple natural disaster management strategies as new temporal data is collected.

12. The article of manufacture of claim 10, wherein using the collection of static demographic data to estimate risk of impact of the parameter of the potential natural disaster on the multiple populated areas based on the estimated spatio-temporal distribution of the parameter comprises overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas.

13. The article of manufacture of claim 12, wherein overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas comprises facilitating prioritization of an area with a higher probability of occurrence.

14. A system for estimating risk of impact of a natural disaster on a populated area, comprising:

a memory; and

at least one processor coupled to the memory and operative for;

estimating a spatio-temporal distribution of a parameter of a potential natural disaster based on a collection of dynamic natural disaster modeling information, wherein the collection of dynamic natural disaster modeling information comprises at least information derived from a global weather model and satellite data, and wherein said estimating the spatio-temporal distribution comprises;

inputting the dynamic natural disaster modeling information to an instance of a weather forecast model to compute simulation results for multiple natural disaster parameters for an area at a given time interval; and

incorporating the simulation results produced on each time step within the given time interval into the estimate of the spatio-temporal distribution of a parameter of the potential natural disaster;

estimating risk of impact of the parameter of the potential natural disaster on multiple populated areas based on (i) the estimated spatio-temporal distribution of the parameter and (ii) a collection of static demographic data comprising information pertaining at least to topography, water bodies, and population occupation, wherein said estimating the risk of impact comprises;

overlaying the static demographic data with the estimated spatio-temporal distribution; and

applying a weight to each of the multiple populated areas based on (i) historical natural disaster incidents for each of the multiple populated areas and (ii) impact corresponding to said historical natural disaster incidents for each of the multiple populated areas;

using the estimated risk of impact of the parameter of the potential natural disaster on the multiple populated areas to generate multiple natural disaster management strategies for the multiple populated areas; and

generating at least one key performance indicator for assessing risk for each of the multiple natural disaster management strategies.

15. The system of claim 14, wherein the at least one processor coupled to the memory is further operative for updating each of the multiple natural disaster management strategies as new temporal data is collected.

16. The system of claim 14, wherein the at least one processor coupled to the memory operative for using the collection of static demographic data to estimate risk of impact of the parameter of the potential natural disaster on the multiple populated areas based on the estimated spatio-temporal distribution of the parameter is further operative for overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas.

17. The system of claim 16, wherein the at least one processor coupled to the memory operative for overlapping the collection of static demographic data and the estimated spatio-temporal distribution of the parameter to generate multiple outputs on a map to assess a probability of the parameter of the potential natural disaster occurring at the multiple populated areas is further operative for facilitating prioritization of an area with a higher probability of occurrence.