IP Library › Granted Patent US 12,742,905
Granted Patent B2
US 12,742,905 · App. 18/564,961 · Granted Sep 22, 2026

Optimizing a probability of precipitation forecast

Inventors: William B. Gail (Boulder, CO); Brett Basarab (Longmont, CO); William Myers (Boulder, CO)
Assignee: Google LLC
G01W1/10G01W1/14G01W1/18
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 12,742,905
App. No.
18/564,961
Granted
Sep 22, 2026
Kind
B2
Abstract

A method of optimizing a probability of precipitation forecast is provided. The method includes uniquely associating, based on a data segment definition, a spatiotemporal subregion with a probability of precipitation forecasting algorithm of two or more probability of precipitation forecasting algorithms. The method further includes selecting climatological data meeting the data segment definition and calibrating, using the selected climatological data meeting the data segment definition, the probability of precipitation forecasting algorithm associated with the spatiotemporal subregion.

Claims (42)

1 . A method comprising:

uniquely associating, based on a data segment definition, a spatiotemporal subregion with a precipitation forecasting algorithm of two or more precipitation forecasting algorithms;

selecting climatological data meeting the data segment definition; and

calibrating, using the climatological data meeting the data segment definition, the precipitation forecasting algorithm associated with the spatiotemporal subregion to generate a calibrated precipitation forecasting algorithm.

2 . The method of claim 1 , wherein the two or more precipitation forecasting algorithms are associated with a region including the spatiotemporal subregion.

3 . The method of claim 2 , wherein uniquely associating, based on the data segment definition, the spatiotemporal subregion with the precipitation forecasting algorithm comprises determining if an initial precipitation forecast value from one of the two or more precipitation forecasting algorithms meets the data segment definition.

4 . The method of claim 1 , wherein the climatological data comprises one or more historical precipitation values associated with a spatial region of the spatiotemporal subregion.

5 . The method of claim 4 , wherein the one or more historical precipitation values associated with the spatial region of the spatiotemporal subregion and a seasonal attribute of the climatological data meet the data segment definition.

6 . The method of claim 1 , wherein the data segment definition comprises at least a precipitation threshold and a seasonal attribute.

7 . The method of claim 1 , further comprising using the calibrated precipitation forecasting algorithm to generate a precipitation forecast value for the spatiotemporal subregion.

8 . A system comprising:

a storage system with instructions configured to:

uniquely associate, based on a data segment definition, a spatiotemporal subregion with a precipitation forecasting algorithm of two or more precipitation forecasting algorithms;

select climatological data meeting the data segment definition; and

calibrate, using the climatological data meeting the data segment definition, the precipitation forecasting algorithm associated with the spatiotemporal subregion to generate a calibrated precipitation forecasting algorithm; and

a processing system communicatively coupled to the storage system.

9 . The system of claim 8 , wherein the two or more precipitation forecasting algorithms are associated with a region including the spatiotemporal subregion.

10 . The system of claim 8 , wherein uniquely associating, based on the data segment definition, the spatiotemporal subregion with the precipitation forecasting algorithm comprises determining if an initial precipitation forecast value from one of the two or more precipitation forecasting algorithms meets the data segment definition.

11 . The system of claim 8 , wherein the climatological data comprises one or more historical precipitation values associated with a spatial region of the spatiotemporal subregion.

12 . The system of claim 11 , wherein the one or more historical precipitation values and a seasonal attribute of the climatological data meet the data segment definition.

13 . The system of claim 8 , wherein the data segment definition comprises at least a precipitation threshold and a seasonal attribute.

14 . The system of claim 8 , wherein the processing system is further configured to: use the calibrated precipitation forecasting algorithm to generate a precipitation forecast value for the spatiotemporal subregion and provide the precipitation forecast value.

15 . A method comprising:

selecting a data segment definition;

selecting a precipitation forecasting algorithm;

calibrating, using climatological data meeting the data segment definition, the precipitation forecasting algorithm to generate a calibrated precipitation forecasting algorithm;

determining a skill value and a reliability value of the calibrated precipitation forecasting algorithm; and

associating the skill value and the reliability value of the calibrated precipitation forecasting algorithm with a combination of the precipitation forecasting algorithm and the data segment definition.

16 . The method of claim 15 , further comprising determining, based on the skill value and the reliability value of the calibrated precipitation forecasting algorithm, an optimized combination of the precipitation forecasting algorithm and the data segment definition.

17 . The method of claim 15 , further comprising storing an association between the skill value and the reliability value of the calibrated precipitation forecasting algorithm and the combination of the precipitation forecasting algorithm and the data segment definition.

18 . The method of claim 15 , wherein associating the skill value and the reliability value with the combination of the precipitation forecasting algorithm and the data segment definition comprises associating an aggregation of the skill value and the reliability value with the combination of the precipitation forecasting algorithm and the data segment definition.

19 . A system comprising:

a storage system with instructions configured to:

select a data segment definition;

select a precipitation forecasting algorithm from two or more precipitation forecasting algorithms;

calibrate, using climatological data meeting the data segment definition, the precipitation forecasting algorithm to generate a calibrated precipitation forecasting algorithm;

determine a skill value and a reliability value of the calibrated precipitation forecasting algorithm; and

associate the skill value and the reliability value of the calibrated precipitation forecasting algorithm with a combination of the precipitation forecasting algorithm and the data segment definition; and

a processing system communicatively coupled to the storage system.

20 . The system of claim 19 , further comprising determining, based on the skill value and the reliability value of the calibrated precipitation forecasting algorithm, an optimized combination of the precipitation forecasting algorithm and the data segment definition.

21 . The system of claim 19 , further comprising storing an association between the skill value and the reliability value of the calibrated precipitation forecasting algorithm and the combination of the precipitation forecasting algorithm and the data segment definition.

22 . The system of claim 19 , wherein associating the skill value and the reliability value with the combination of the precipitation forecasting algorithm and the data segment definition comprises associating an aggregation of the skill value and the reliability value with the combination of the precipitation forecasting algorithm and the data segment definition.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 7, 2024
From: GLOBAL WEATHER CORPORATION
To: GOOGLE LLC
Reel/Frame 069178/0651 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2023
From: GAIL, WILLIAM B.; BASARAB, BRETT; MYERS, WILLIAM
To: GLOBAL WEATHER CORPORATION
Reel/Frame 065757/0540 →
MERGER Recorded Dec 5, 2023
From: GLOBAL WEATHER CORPORATION
To: GOOGLE LLC
Reel/Frame 065757/0581 →
Continuity (1)
Related Publication 20240184013A1 · Jun 6, 2024
References Cited (24)
US 10197706B1 · Cai et al. · 2019 [cited by applicant]
US 12443739B2 · Mohammed · 2025 [cited by examiner]
US 12554874B2 · Mohammed · 2026 [cited by examiner]
US 20140350856A1 · Lambie et al. · 2014 [cited by applicant]
US 20150198452A1 · Gupta · 2015 [cited by examiner]
US 20160299255A1 · Dail et al. · 2016 [cited by applicant]
US 20190018918A1 · Wood et al. · 2019 [cited by applicant]
US 20200309994A1 · Eckel et al. · 2020 [cited by applicant]
US 20200398959A1 · Pomerantz · 2020 [cited by examiner]
US 20210129078A1 · Regan · 2021 [cited by examiner]
US 20230250495A1 · Osborn · 2023 [cited by examiner]
US 20230364554A1 · Romaniello · 2023 [cited by examiner]
US 20240054513A1 · Ma · 2024 [cited by examiner]
US 20240061977A1 · Ling · 2024 [cited by examiner]
US 20240354851A1 · Stolt · 2024 [cited by examiner]
JP H05060879A · 1993 [cited by applicant]
JP 2010060444A · 2010 [cited by applicant]
JP 2010243483A · 2010 [cited by applicant]
JP 2020106406A · 2020 [cited by applicant]
WO 2018043252A1 · 2018 [cited by applicant]
WO 2021080107A1 · 2021 [cited by applicant]
International Search Report and Written Opinion for PCT Application No. PCT/US2021/034757, mailed on Feb. 16, 2022, 11 pages. [cited by applicant]
Office Action for Japanese Application No. 2023-573220 (with English translation), mailed Nov. 12, 2024, 13 pages. [cited by applicant]
First Office Action for Chinese Application No. 202180098757.7 (with English translation), dated Mar. 19, 2026, 16 pages. [cited by applicant]