Method and system for forecasting events and threats based on geospatial modeling

• US 20050222879A1
• Filed: 04/04/2005
• Published: 10/06/2005
• Est. Priority Date: 04/02/2004
• Status: Active Grant

• Current Assignee: Radiant Analytic Solutions, Inc. (Galileo Parent, Inc.), United States Government In The Name of The Defense Advanced Research Projects Agency
• Original Assignee: Spadac Inc.
• Inventors: Willis, Larry E., Willis, Ruth P., Dumas, Mark E.
• Granted Patent: US 7,120,620 B2
• Time in Patent Office: Days
• US Class Current: 705/5
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G09B 29/007 using computer methods

Abstract

A forecasting engine and method assists in forecasting occurrences of identifiable events and/or threats based on signature and/or pattern matching. The present invention derives signature for event-types based on a comparison of actual event data with pre-established representational surfaces. The surfaces represent proximity measurements and analysis associated with elements of the geospatial boundary being considered. The measurements and analysis can consider a vast array of potential variables of interest in order to provide a comprehensive, robust forecasting engine. In one embodiment, the present invention considers past data associated with several event-types in order to arrive at an assessment.

Claims

1. A geospatial event forecasting engine, comprising:

a boundary component for establishing a geospatial boundary and a grid containing a plurality of cells within said boundary;

a layer component for establishing at least one layer imposed upon the grid, the layer being indicative of geospatial characteristics of at least one variable of interest;

a proximity component for identifying a proximity measurement of a cell element for each cell to the variable of interest, and for indexing said proximity measurement for each cell;

a signature derivation component for receiving geospatial information related to one or more past events of at least one event type, including location information for said one or more past events, said signature derivation component further identifying and indexing a proximity measurement from the location information for each of said one or more events to the at least one variable of interest, and deriving a signature pattern for said event type; and

an event likelihood determinant component for determining a level of signature match between said derived signature pattern and at least one cell of said plurality of cells through comparison with said proximity measurement.

2. The engine of claim 1 wherein said at least one variable of interest is discrete.

3. The engine of claim 1 wherein said at least one variable of interest is continuous.

4. The engine of claim 1 wherein said signature derivation component receives geospatial information related to one or more past events of a plurality of event types, including a first and second event type, and wherein said event likelihood determinant component provides an assessment of the likely location of a first event-type occurrence.

5. The engine of claim 1 wherein said cell element is the cell center point for each of said cells.

6. The engine of claim 1 wherein said signature derivation component establishes said signature using a probability density function.

7. The engine of claim 1 wherein said layer component establishes a plurality of layers, and wherein at least one of said layers is indicative of geospatial characteristics of a plurality of variables.

8. The engine of claim 7 wherein said proximity component identifies and indexes a plurality of proximity measurements for each cell, and wherein said signature derivation component identifies and indexes a plurality of proximity measurements from the location information for each of said one or more events to the one or more variables of interest for each of said layers.

9. The engine of claim 1 wherein said proximity measurement is a nearest neighbor distance measurement or a nearest neighbor value measurement.

10. The engine of claim 1 wherein said event probability determinant component determines a level of signature match for each of said plurality of cells.

11. The engine of claim 10 wherein said event probability determinant component determines a level of signature match by determining a score indicative of each cell'"'"'s compatibility with the event type signature pattern.

12. The engine of claim 11 wherein said score for each cell can be plotted on a choropleth graph.

13. The engine of claim 1 wherein said at least one variable of interest is provided with a plurality of feature types individually indexed by a respective feature identifier.

14. A method for forecasting events using geospatial information, comprising the steps of:

establishing a geospatial boundary and a grid containing a plurality of cells within said boundary;

establishing at least one layer imposed upon the grid, the layer being indicative of geospatial characteristics of at least one variable of interest;

identifying a proximity measurement of a cell element for each cell to the variable of interest, and for indexing said proximity measurement for each cell;

receiving geospatial information related to one or more past events of at least one event type, including location information for said one or more past events;

identifying and indexing a proximity measurement from the location information for each of said one or more events to the at least one variable of interest;

deriving a signature pattern for said event type; and

determining a level of signature match between said derived signature pattern and at least one cell of said plurality of cells through comparison with said proximity measurement.

15. The method of claim 14 wherein said at least one variable of interest is discrete.

16. The method of claim 14 wherein said at least one variable of interest is continuous.

17. The method of claim 14 wherein said signature derivation component receives geospatial information related to one or more past events of a plurality of event types, including a first and second event type, and wherein said event likelihood determinant component provides an assessment of the likely location of a first event-type occurrence.

18. The method of claim 14 wherein said event probability determinant component establishes said signature using a probability density function.

19. The method of claim 14 wherein said layer component establishes a plurality of layers, and wherein at least one of said layers is indicative of geospatial characteristics of a plurality of variables.

20. The method of claim 19 wherein said proximity component identifies and indexes a plurality of proximity measurements for each cell, and wherein said signature derivation component identifies and indexes a plurality of proximity measurements from the location information for each of said one or more events to the one or more variables of interest for each of said layers.

21. The method of claim 14 wherein said proximity measurement is a nearest neighbor distance measurement or a nearest neighbor value measurement.

22. The method of claim 14 wherein said event probability determinant component determines a level of signature match for each of said plurality of cells.

23. The method of claim 14 wherein said event probability determinant component determines whether there is a signature match by determining a score indicative of each cell'"'"'s compatibility with the event type signature.

24. The method of claim 23 wherein said score for each cell can be plotted on a choropleth graph.

25. The method of claim 14 wherein said at least one variable of interest is provided with a plurality of feature types individually indexed by a respective feature identifier.

26. A system for forecasting threats, comprising:

a geospatial database storing boundary and layer information for a plurality of areas of interest, said layer information being indicative of geospatial characteristics of a plurality of variables of interest;

a proximity engine for identifying and indexing proximity measurements to each of said variables of interest for a plurality of cells within each area of interest;

a signature derivation component for receiving geospatial information related to one or more past events of at least one event type, including location information for said one or more past events, and identifying and indexing a proximity measurement from the location information for each of said one or more events to the at least one variable of interest, and deriving a signature pattern for said event type; and

a threat forecasting component for determining a level of signature match between said derived signature pattern and at least one cell of said plurality of cells through comparison with said proximity measurements, said threat forecasting component being capable of rendering a two-dimensional display of an area of interest associated with said plurality of cells, said display including a representation of said level of signature match.

27. A geospatial event forecasting engine, comprising:

a boundary component for establishing a geospatial boundary and a grid containing a plurality of cells within said boundary;

a layer component for establishing at least one layer imposed upon the grid, the layer being indicative of geospatial characteristics of at least one variable of interest;

a proximity component for identifying a proximity measurement of a cell element for each cell to the variable of interest, and for indexing said proximity measurement for each cell;

a signature derivation component for receiving geospatial information related to one or more past events of at least one event type, including location information for said one or more past events, said signature derivation component further identifying and indexing a proximity measurement from the location information for each of said one or more events to the at least one variable of interest, and deriving a signature pattern for said event type; and

an event likelihood determinant component for determining a level of signature match between said derived signature pattern and at least one cell of said plurality of cells through comparison with said proximity measurement; and

a signature transfer component for applying said established signature from said first boundary to said indexed proximity measurements of said second boundary and determining a level of signature match between said established signature and at least one cell of said plurality of cells in said second boundary.