IP Library Granted Patent US 10,534,784
Granted Patent B2
US 10,534,784 · App. 15/823,871 · Granted Jan 14, 2020

Formulation and delivery of dynamic, severity-based weather peril scoring

Inventors: Ellen Dee Cousins (Rockville, MD); Stefan Francis Cecelski (Odenton, MD)
Assignee: Athenium, LLC
G06F16/24578G06F16/284G06F16/29G06F17/18G06Q40/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,534,784
App. No.
15/823,871
Granted
Jan 14, 2020
Kind
B2
Abstract

A computer-based method of formulating and delivering dynamic, severity-based weather peril scoring includes ingesting human-observed weather data and radar weather data, applying a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells, for each area/grid cell: calculating, with a computer-based processor, a first severity-weighted risk index for at least one weather peril based on the human-observed weather data, calculating, with the computer-based processor, a second severity-weighted risk index for the at least one weather peril based on the radar weather data, and blending, with the computer-based processor, the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index.

Claims (130)

1. A computer-based method of formulating and delivering dynamic, severity-based weather peril scoring, the method comprising:

ingesting human-observed weather data and radar weather data;

applying a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells;

for each area/grid cell:

calculating, with a computer-based processor, a first severity-weighted risk index for at least one weather peril based on the human-observed weather data;

calculating, with the computer-based processor, a second severity-weighted risk index for the at least one weather peril based on the radar weather data; and

blending, with the computer-based processor, the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein calculating the first severity-weighted risk indices comprises:

collecting the human-observed weather data;

calculating raw probabilities of damage from the at least one weather peril based on the human-observed weather data;

correcting the raw probabilities to account for population bias; and

calculating the actual first severity-weighted risk indices based on the corrected probabilities.

2. The computer-based method of claim 1 , wherein calculating the second severity-weighted risk indices comprises:

collecting the radar weather data;

calculating raw probabilities of damage from the at least one weather peril based on the radar weather data; and

calculating the actual second severity-weighted risk indices based on the corrected probabilities.

3. The computer-based method of claim 1 , wherein blending the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index comprises:

weighting the first severity-weighted risk index based on population density;

weighting the second severity-weighted risk index based on radar quality;

weighting the second severity-weighted risk index more than the first severity-weighted risk index.

4. The computer-based method of claim 1 , further comprising applying spatial smoothing to the first severity-weighted risk indices, the second severity-weighted risk indices, and/or the blended risk indices across the areas/grid cells to produce at least smoothed-out blended risk indices.

5. The computer-based method of claim 4 , wherein the spatial smoothing for a given area/grid cell comprises calculating a risk value for the given area/grid cell as a statistical average of the blended risk value for that given cell and risk values for all other areas/grid cells within a certain distance of that given cell.

6. The computer-based method of claim 4 , further comprising:

categorizing each area/grid cell into one of a plurality of possible risk zones.

7. The computer-based method of claim 6 , wherein categorizing each area/grid cell into one of a plurality of possible risk zones comprises:

calculating a first risk score by percentile-based binning the smoothed-out blended risk indices;

calculating a second risk score by equal-interval binning the smoothed-out blended risk indices; and

averaging the first risk score and the second risk score.

8. The computer-based method of claim 1 , further comprising:

enabling a human user to access weather peril scoring data from a user device, wherein the weather peril scoring data comprises: data superimposed on a map, with color-coded cells, categorized by peril scores.

9. A computer-based system configured to formulate and deliver dynamic, severity-based weather peril scoring, the system comprising:

a computer-based processor, and

a computer-based memory coupled to the computer-based processor, wherein the computer-based memory stores instructions which, when executed by the computer-based processor, cause the computer-based processor to:

apply a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells; and

for each area/grid cell:

calculate a first severity-weighted risk index for at least one weather peril based on ingested human-observed weather data;

calculate a second severity-weighted risk index for the at least one weather peril based on ingested radar weather data; and

blend the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to calculate the first severity-weighted risk indices by:

collecting the human-observed weather data;

calculating raw probabilities of damage from the at least one weather peril based on the human-observed weather data;

correcting the raw probabilities to account for population bias; and

calculating the actual first severity-weighted risk indices based on the corrected probabilities.

10. The computer-based system of claim 9 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to calculate the second severity-weighted risk indices by:

collecting the radar weather data;

calculating raw probabilities of damage from the at least one weather peril based on the radar weather data; and

calculating the actual second severity-weighted risk indices based on the corrected probabilities.

11. The computer-based system of claim 9 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to produce the blended risk index by:

weighting the first severity-weighted risk index based on population density,

weighting the second severity-weighted risk index based on radar quality; and

weighting the second severity-weighted risk index more than the first severity-weighted risk index.

12. The computer-based system of claim 11 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to apply spatial smoothing to the first severity-weighted risk indices, the second severity-weighted risk indices, and/or the blended risk indices across the areas/grid cells to produce at least smoothed-out blended risk indices.

13. The computer-based system of claim 12 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to apply the spatial smoothing for a given area/grid cell by calculating a risk value for the given area/grid cell as a statistical average of the blended risk value for that given cell and risk values for all other areas/grid cells within a certain distance of that given cell.

14. The computer-based system of claim 12 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to:

categorize each area/grid cell into one of a plurality of possible risk zones.

15. The computer-based system of claim 14 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor categorize each area/grid cell into one of a plurality of possible risk zones by:

calculating a first risk score by percentile-based binning the smoothed-out blended risk indices;

calculating a second risk score by equal-interval binning the smoothed-out blended risk indices; and

averaging the first risk score and the second risk score.

16. The computer-based system of claim 9 , further comprising:

a computer-based user device configured to enable a human user to access weather peril scoring data, wherein the weather peril scoring data comprises: data superimposed on a map, with color-coded cells, categorized by peril scores.

17. A computer-based method of formulating and delivering dynamic, severity-based weather peril scoring, the method comprising:

ingesting human-observed weather data and radar weather data;

applying a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells;

for each area/grid cell:

calculating, with a computer-based processor, a first severity-weighted risk index for at least one weather peril based on the human-observed weather data;

calculating, with the computer-based processor, a second severity-weighted risk index for the at least one weather peril based on the radar weather data; and

blending, with the computer-based processor, the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein calculating the second severity-weighted risk indices comprises:

collecting the radar weather data;

calculating raw probabilities of damage from the at least one weather peril based on the radar weather data; and

calculating the actual second severity-weighted risk indices based on the corrected probabilities.

18. A computer-based method of formulating and delivering dynamic, severity-based weather peril scoring, the method comprising:

ingesting human-observed weather data and radar weather data;

applying a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells;

for each area/grid cell:

calculating, with a computer-based processor, a first severity-weighted risk index for at least one weather peril based on the human-observed weather data;

calculating, with the computer-based processor, a second severity-weighted risk index for the at least one weather peril based on the radar weather data; and

blending, with the computer-based processor, the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein blending the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index comprises:

weighting the first severity-weighted risk index based on population density;

weighting the second severity-weighted risk index based on radar quality;

weighting the second severity-weighted risk index more than the first severity-weighted risk index.

19. A computer-based method of formulating and delivering dynamic, severity-based weather peril scoring, the method comprising:

ingesting human-observed weather data and radar weather data;

applying a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells;

for each area/grid cell:

calculating, with a computer-based processor, a first severity-weighted risk index for at least one weather peril based on the human-observed weather data;

calculating, with the computer-based processor, a second severity-weighted risk index for the at least one weather peril based on the radar weather data; and

blending, with the computer-based processor, the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index, and

applying spatial smoothing to the first severity-weighted risk indices, the second severity-weighted risk indices, and/or the blended risk indices across the areas/grid cells to produce at least smoothed-out blended risk indices.

20. The computer-based method of claim 19 , wherein the spatial smoothing for a given area/grid cell comprises calculating a risk value for the given area/grid cell as a statistical average of the blended risk value for that given cell and risk values for all other areas/grid cells within a certain distance of that given cell.

21. The computer-based method of claim 19 , further comprising:

categorizing each area/grid cell into one of a plurality of possible risk zones.

22. The computer-based method of claim 21 , wherein categorizing each area/grid cell into one of a plurality of possible risk zones comprises:

calculating a first risk score by percentile-based binning the smoothed-out blended risk indices;

calculating a second risk score by equal-interval binning the smoothed-out blended risk indices; and

averaging the first risk score and the second risk score.

23. A computer-based system configured to formulate and deliver dynamic, severity-based weather peril scoring, the system comprising:

a computer-based processor, and

a computer-based memory coupled to the computer-based processor, wherein the computer-based memory stores instructions which, when executed by the computer-based processor, cause the computer-based processor to:

apply a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells; and

for each area/grid cell:

calculate a first severity-weighted risk index for at least one weather peril based on ingested human-observed weather data;

calculate a second severity-weighted risk index for the at least one weather peril based on ingested radar weather data; and

blend the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to calculate the second severity-weighted risk indices by:

collecting the radar weather data;

calculating raw probabilities of damage from the at least one weather peril based on the radar weather data; and

calculating the actual second severity-weighted risk indices based on the corrected probabilities.

24. A computer-based system configured to formulate and deliver dynamic, severity-based weather peril scoring, the system comprising:

a computer-based processor, and

a computer-based memory coupled to the computer-based processor, wherein the computer-based memory stores instructions which, when executed by the computer-based processor, cause the computer-based processor to:

apply a grid that has a plurality of cells to a map of a geographical region to divide the geographical region into a plurality of areas, with each area being defined by a corresponding one of the grid cells; and

for each area/grid cell:

calculate a first severity-weighted risk index for at least one weather peril based on ingested human-observed weather data;

calculate a second severity-weighted risk index for the at least one weather peril based on ingested radar weather data; and

blend the first severity-weighted risk index and the second severity-weighted risk index to produce a blended risk index,

wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to produce the blended risk index by:

weighting the first severity-weighted risk index based on population density;

weighting the second severity-weighted risk index based on radar quality; and

weighting the second severity-weighted risk index more than the first severity-weighted risk index.

25. The computer-based system of claim 24 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to apply spatial smoothing to the first severity-weighted risk indices, the second severity-weighted risk indices, and/or the blended risk indices across the areas/grid cells to produce at least smoothed-out blended risk indices.

26. The computer-based system of claim 25 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to apply the spatial smoothing for a given area/grid cell by calculating a risk value for the given area/grid cell as a statistical average of the blended risk value for that given cell and risk values for all other areas/grid cells within a certain distance of that given cell.

27. The computer-based system of claim 25 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor to:

categorize each area/grid cell into one of a plurality of possible risk zones.

28. The computer-based system of claim 27 , wherein the instructions, when executed by the computer-based processor, further cause the computer-based processor categorize each area/grid cell into one of a plurality of possible risk zones by:

calculating a first risk score by percentile-based binning the smoothed-out blended risk indices;

calculating a second risk score by equal-interval binning the smoothed-out blended risk indices; and

averaging the first risk score and the second risk score.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 8, 2019
From: ATHENIUM ANALYTICS LLC
To: ATHENIUM LLC
Reel/Frame 048818/0821 →
CHANGE OF NAME Recorded Jul 5, 2018
From: WEATHER ANALYTICS LLC
To: ATHENIUM ANALYTICS LLC
Reel/Frame 046491/0721 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 28, 2017
From: COUSINS, ELLEN DEE; CECELSKI, STEFAN FRANCIS
To: WEATHER ANALYTICS LLC
Reel/Frame 044233/0560 →
Continuity (2)
Provisional Application 62502115 · May 5, 2017
Related Publication 20180322123A1 · Nov 8, 2018
Cited By (4)
US 12,360,286 US 12,360,287 US 12,536,594 US 12,585,837