Method and system for refining weather forecasts using point observations

• US 10,495,785 B2
• Filed: 04/03/2014
• Issued: 12/03/2019
• Est. Priority Date: 04/04/2013
• Status: Active Grant

• Current Assignee: Sky Motion Research, ULC
• Original Assignee: Sky Motion Research, ULC
• Inventors: Leblanc, Andre
• Primary Examiner(s): Rivera Vargas, Manuel A
• Application Number:
  US14/244,516
• Publication Number:
  US 20140372039A1
• Time in Patent Office: 2,070 Days
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09

Abstract

Provided are methods, devices and non-transitory computer readable storage mediums to generate a more accurate weather forecast by utilizing actual observation of a weather event in a particular location and time. For example, the observation data may be received from a user device and contain information indicative of a weather event that the user observed. Alternatively, or additionally, the observation data may be automatically generated by one or more sensors placed in certain locations and transmitted to a central server automatically upon detecting an observation. The observation data may be used to predict a weather forecast of a location that corresponds to, or is otherwise related to the particular location in which the observed event occurred.

Claims

1. A computer-implemented method, comprising:

receiving, from a remote device, weather-related observation data based on input from a user of the remote device, the weather-related observation data indicating a weather-related event at a location and a time;

determining a trust rating indicative of a reliability of the weather-related observation data by comparing the weather-related observation data to objective weather data;

determining, based on the trust rating, a weight associated with the weather-related observation data;

setting a value of a pixel in an image based on the weather-related observation data and the weight, the pixel associated with the location;

generating a weather forecast based on the image; and

outputting the weather forecast.

2. The method of claim 1, wherein the image is associated with the time.

3. The method of claim 2, wherein the weather forecast is generated based further on a second image associated with a different time.

4. The method of claim 2, wherein the image further includes a second pixel associated with a second location, the method further comprising:

receiving, from a second remote device, second weather-related observation data input by a second user of the second remote device, the second weather-related observation data indicating a second weather-related event at the second location; and

setting the second pixel to a second value based on the second weather-related observation data and a second weight, the second weight determined based on a second trust rating associated with the second weather-related observation data.

5. The method of claim 1, wherein comparing the weather-related observation data to the objective weather data includes determining a likelihood of the weather-related event indicated by the weather-related observation data occurring based on the objective weather data.

6. The method of claim 5, wherein the objective weather data indicates a temperature, an air pressure, or a combination thereof and the weather-related event indicates a particular precipitation type.

7. The method of claim 1, wherein the weather-related event comprises at least one of hail, wind, lightening, temperature, precipitation and intensity of sunlight.

8. The method of claim 1, comprising:

storing the received weather-related observation data;

producing a statistic associated with the stored weather-related observation data, the statistic comprising information indicative of a number of remote devices that have received the weather forecast; and

outputting at least part of the statistic to the remote device.

9. The method of claim 1, further comprising distributing an application to the remote device, the application configured to present a graphical user interface configured to generate the weather-related observation data based the input received from the user.

10. The method of claim 1, wherein the weather forecast indicates a likely precipitation type for an area and, for each rate of a plurality of rates, a probability of the likely precipitation type occurring at the rate.

11. The method of claim 1, wherein the weather forecast is sent to another remote device distinct from the remote device, the method further comprising transmitting, to the remote device, an indication that the other remote device benefitted from the weather-related observation data.

12. The method of claim 1, wherein the image further includes a second pixel associated with a second location, the method further comprising setting a second value of the second pixel based on the weather-related observation data, the weight, and a distance between the location and the second location.

13. A device comprising:

one or more processors;

a memory that stores instructions for the one or more processors; and

a communication module to connect to a remote device via a communication network, wherein when the one or more processors execute the instructions stored in the memory, the device is caused to;

receive, from the remote device, weather-related observation data based on user input from a user of the remote device, the weather-related observation data indicating a weather-related event at a time and a location;

determine a trust rating indicative of a reliability of the user by comparing the weather-related observation data to objective weather data;

determine, based on the trust rating, a weight associated with the weather-related observation data;

set a value of a pixel in an image based on the weather-related observation data and the weight, the pixel associated with the location;

generate a weather forecast based on the image; and

output the weather forecast.

14. The device of claim 13, wherein the one or more processors are further caused to receive, from a second source, automatically generated measurements, wherein the weather forecast is generated based further on the automatically generated measurements, and wherein the weather forecast indicates an area predicted to be affected by the weather-related event, the area identified based on the automatically generated measurements.

15. The device of claim 14, wherein the automatically generated measurements include radar measurements.

16. The device of claim 13, wherein, when the one or more processors execute the instructions, the device is further caused to:

receive, from a second remote device, second weather-related observation data based on second input from a second user of the second remote device; and

set a value of a second pixel in the image based on the second weather-related observation data and a weight associated with the second user.

17. The device of claim 13, wherein, when the one or more processors execute the instructions, the device is further caused to:

store the received weather-related observation data;

produce a statistic about the stored weather-related observation data, the statistic comprising information indicative of a number of remote devices that have received the weather forecast; and

output at least part of the statistic to the remote device.

18. The device of claim 13, wherein comparing the weather-related observation data to the objective weather data includes determining a likelihood of the weather-related event indicated by the weather-related observation data occurring based on the objective weather data.

19. A system comprising a server and a remote device that is connected to the server over a communication network, wherein:

the server comprises one or more processors and a non-transitory computer readable medium storing a program causing the one or more processors to execute a weather forecast generation process, the weather forecast generation process comprising;

receiving, from a remote device, weather-related observation data based on input from a user of the remote device, the weather-related observation data indicating a weather-related event at a location and a time;

determining a trust rating indicative of a reliability of the user by comparing the weather-related observation data to objective weather data;

determining, based on the trust rating, a weight associated with the weather-related observation data;

setting a value of a pixel in an image based on the weather-related observation data and the weight, the pixel associated with the location;

generating a weather forecast based on the image; and

outputting the weather forecast; and

the remote device comprises a computer, a display and a non-transitory computer memory storing a program causing the computer to execute a process comprising;

obtaining the weather forecast outputted from the server over the communication network; and

causing, on the display, presentation of at least part of the weather forecast.