System, method and program product for providing populace centric weather forecasts

Patent metadata

Field	Value
Publication number	US-10267950-B2
Application number	US-201113251889-A
Country	US
Kind code	B2
Filing date	Oct 3, 2011
Priority date	Oct 3, 2011
Publication date	Apr 23, 2019
Grant date	Apr 23, 2019

Abstract

A populace centric weather forecast system, method of forecasting weather and a computer program product therefor. A forecasting computer applies a grid to a forecast area and provides a weather forecast for each grid cell. Area activity data sources indicate human activity in the forecast area. A dynamic selection module iteratively identifies grid cells for refinement in response to the weather forecast and to indicated/expected human activity. The dynamic selection module provides the forecasting computer with a refined grid for each identified grid cell in each iteration. The forecasting computer provides a refined weather forecast in each iteration.

First claim

What is claimed is:

1. A populace centric weather forecast system comprising:
a forecasting computer applying a dynamic grid to a forecast area and providing a weather forecast for each grid cell;
one or more area activity data sources indicating human presence in said forecast area;
one or more area activity sensors collecting signals of real time activity in said area, said one or more area activity sensors including user locations collected from at least one cell phone provider anonymously detecting user geolocations in remote locations in said forecast area, human activity in a grid cell including human presence and real time activity; and
a dynamic selection module selectively marking cells in said dynamic grid complete and iteratively identifying unmarked grid cells in each iteration for further refinement responsive to said weather forecast and indicated said human activity, in each iteration
said dynamic selection module identifies only grid cells with both weather and human activity for further refinement and marks complete all grid cells not identified for further refinement, all grid cells marked complete being omitted from refinement in subsequent iterations,
said dynamic selection module provides said forecasting computer with a current grid omitting complete cells for further weather forecasting and including a refined grid for each identified said grid cell in said each iteration, wherein omitting cells reduces the weather forecast area and reducing the weather forecast area reduces the data considered for forecasting weather to only the refined gridded area, and
said forecasting computer provides a more comprehensive weather forecast for the reduced weather forecast area from said current grid in said each iteration,

wherein each final dynamic grid causes the resulting final weather map for the entire said forecast area to have a finer resolution weather forecast displayed in inclement weather affected areas with humans present than in areas unaffected by weather or free of human activity, whereby final weather maps for forecasts of said forecast area with different human activity in one or more locations in said forecast area have different resolutions in said one or more locations and said forecasting computer arrives at said each final weather map without post solution activity.

2. A populace centric weather forecast system as in claim 1 , wherein said one or more area activity data sources include historical data and projected data, said real time activity includes transient activity indicated from said one or more area activity sensors, and said one or more area activity sensors further including traffic sensors detecting traffic jams or intense traffic.

3. A populace centric weather forecast system as in claim 2 , wherein said one or more area activity data sources include event data, demographic data, historical incident data, weather sensor data and geodata, and said projected data including population scheduled to be in a cell.

4. A populace centric weather forecast system as in claim 3 , wherein said weather sensor data includes real time sensor data, and said real time activity includes transient activity for population passing through a cell.

5. A populace centric weather forecast system as in claim 1 , wherein in each said iteration said forecasting computer overlays said current grid on an area map from a geodatabase and forecasts weather for each grid cell responsive to real time weather sensor data, and wherein whenever event data indicates an event is scheduled for a locale in said inclement weather affected areas, the forecast resolution for the event locale is at the highest resolution.

6. A populace centric weather forecast system as in claim 1 , wherein said one or more area activity data sources comprise dynamic information sources and static information sources, dynamic information including event venue schedules, area wide traffic patterns and population fluidity, and historically hazardous area identification, and static information includes, identified high demographic concentration areas.

7. A populace centric weather forecast system as in claim 6 , wherein said forecast area includes at least one event venue located in an otherwise unpopulated locale, such that whenever said event venue schedule indicates that during the forecast period no events are scheduled at the event locale, the current grid cell enclosing said event locale is not identified for refinement because of the event venue, and when said event data indicates an event is scheduled, in each iteration the current grid cell enclosing said event locale is identified for refinement with inclement weather.

8. A method of forecasting weather, said method comprising:
overlaying an initial grid on a forecast area, a forecasting computer overlaying said initial grid, said initial grid being a first iteration of a dynamic grid at a first resolution grid cell, said dynamic grid segmenting said forecast area into cells; and iteratively
forecasting the weather during a forecast period for the area enclosed in each cell;
collecting static population information for said forecast area;
collecting dynamic population sensor signals indicating local human activity throughout said forecast area, said dynamic population sensor signals including presence indication signals from at least one cell phone provider anonymously detecting user geolocations in remote locations in said forecast area, any cell enclosing static or transient population being considered as containing human activity;
marking complete each cell with either weather or human inactivity, such that only grid cells with both weather and human activity are not marked complete;
determining if all cells are marked complete; and until all cells are marked complete
refining every cell not marked complete with a refined grid, the current grid omitting all cells marked complete for further weather forecasting and including the refined grid cells, wherein omitting cells for further weather forecasting reduces the weather forecast area and reducing said weather forecast area reduces the data considered,
overlaying said current grid with said refined grid on a respective forecast area not marked complete, and
returning to forecasting the weather in said weather forecast area for the next iteration, wherein in said next iteration the weather is forecast only for each area enclosed in each refined grid cell; and when all cells are marked complete

providing a final weather map for said forecast area, the final dynamic grid causing finer resolution weather displayed in inclement weather areas with human activity than in areas unaffected by weather or free of human activity, whereby the final dynamic grids cause respective final weather maps for forecasts of said forecast area with different human activity in one or more locations in said forecast area to have different resolutions in said one or more locations and iteratively forecasting converges on said final weather map without post solution activity.

9. A method of forecasting weather as in claim 8 , wherein said dynamic population sensor signals further include traffic sensors detecting traffic jams or intense traffic, and when all cells are marked complete, the weather forecast for said forecast area is complete.

10. A method of forecasting weather as in claim 8 , wherein said population information includes historical data and projected data.

11. A method of forecasting weather as in claim 8 , wherein
said human activity includes event data, demographic data, historical incident data, weather sensor data and geodata, and
said forecast area includes at least one event venue located in an otherwi

Assignees

• Cavalcante Victor Fernandes
• Herrmann Ricardo Guimaraes
• Mantripragada Kiran
• Netto Marco Aurelio Stelmar
• Real Lucas Correia Villa
• Souza Cleidson Ronald Botelho De
• IBM

Inventors

• Cavalcante Victor Fernandes
• Herrmann Ricardo Guimaraes
• Mantripragada Kiran
• Netto Marco Aurelio Stelmar
• Real Lucas Correia Villa
• Souza Cleidson Ronald Botelho De

Classifications

• G01W1/10 Primary

  Devices for predicting weather conditions (computers per se G06; display devices G09) · CPC title