Weather forecasting systems and methods

• US 10,613,252 B1
• Filed: 03/17/2016
• Issued: 04/07/2020
• Est. Priority Date: 10/02/2015
• Status: Active Grant

• Current Assignee: Board of Trustees of The University of Alabama (University of Alabama System)
• Original Assignee: Board of Trustees of The University of Alabama (University of Alabama System)
• Inventors: Mecikalski, John R.
• Primary Examiner(s): Patel, Reema
• Assistant Examiner(s): Christopher, Steven M
• Application Number:
  US15/073,304
• Time in Patent Office: 1,482 Days
• Field of Search: None
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06T 2207/30192 Weather; Meteorology

Abstract

A weather forecasting system has a data processing system that receives weather data from one or more sources and processes such data in conjunction with a weather forecasting algorithm in order to forecast weather for one or more geographic regions. In this regard, the weather data is input into a machine learning algorithm, which applies learned weights and relationships to the inputs in order to calculate at least one score indicating a probability that precipitation or other weather event will occur in the future within a certain time period (e.g., within the next 1 hour or some other unit of time) in one or more geographic regions. For each such geographic region, the weather forecasting logic may also predict the extent to which rain or other precipitation, lightning, or other weather event will occur during the time period.

Claims

1. A weather forecasting system, comprising:

memory for storing satellite image data and weather data, the weather data indicating weather forecasts for a geographic region, wherein the weather data includes a plurality of values, each of the values indicating a probability or extent to which a weather event is forecast to occur within the geographic region for a time period in the future;

at least one processor programmed to analyze the satellite image data and the weather data according to a machine-learning algorithm to provide forecast data, wherein the at least one processor is programmed to dynamically select a zone of influence for a sub-region of the geographic region based on weather conditions indicated by the weather data, the zone of influence defining a zone within the geographic region associated with a portion of the satellite image data and the weather data to be analyzed by the at least one processor for determining input variables derived from the satellite image data and the weather data to be used to calculate a forecast score for the sub-region, wherein the at least one processor is configured to analyze the portion of the satellite image data and the weather data within the dynamically-selected zone of influence to determine the input variables, wherein the at least one processor according to the machine-learning algorithm for at least the sub-region is programmed to apply weights to the input variables and to mathematically combine the input variables to provide the forecast score for the forecast data corresponding to the sub-region, the forecast score indicating a probability or extent to which a weather event is forecast by the machine-learning algorithm to occur within the sub-region for a time period in the future; and

an output interface configured to provide an output based on the forecast data.

2. The system of claim 1, wherein the machine-learning algorithm is based on a regression equation.

3. The system of claim 1, wherein the at least one processor is configured to learn the weights by performing a regression analysis on sample input variables relative to at least one predefined output for the machine-learning algorithm.

4. The system of claim 1, wherein at least one of the input variables corresponds to a measurement for at least one pixel of the satellite image data.

5. The system of claim 1, wherein at least one of the input variables corresponds to at least one of the plurality of values of the weather data.

6. The system of claim 1, wherein the output defines a weather map for the geographic region.

7. The system of claim 1, wherein the memory is configured to store topographical data indicative of a topology of the geographic region, and wherein at least one of the input variables is based on the topographical data.

8. The system of claim 1, wherein the at least one processor is programmed to calculate a plurality of interest fields based on the satellite image data and the weather data, each of the interest fields indicative of weather occurring or forecast to occur in at least one sub-region of the geographic region, and wherein the at least one processor is programmed to adjust the zone of influence such that the zone of influence is larger for one of the interest fields relative to another of the interest fields.

9. The system of claim 1, wherein the at least one processor is programmed to calculate at least one interest field based on the satellite image data and the weather data, the at least one interest field indicative of weather occurring or forecast to occur in at least one sub-region of the geographic region, and wherein the at least one processor is programmed to control a size of the zone of influence based on the at least one interest field.

10. The system of claim 9, wherein the at least one interest field relates to wind measured or forecast in at least one sub-region of the geographic region.

11. The system of claim 1, wherein the satellite image data and the weather data are associated with a time period, and wherein the at least one processor is programmed to adjust a size of the zone of influence based on the time period that is associated with the satellite image data and the weather data.

12. A weather forecasting method, comprising:

storing, in memory, satellite image data;

storing, in memory, weather data indicating weather forecasts for a geographic region, the weather predication data including a plurality of values, each of the values indicating a probability or extent to which a weather event is forecast to occur within the geographic region for a time period in the future;

analyzing, by at least one processor, the satellite image data and the weather data;

based on the analyzing, determining by the at least one processor input variables for a machine-learning algorithm for forecasting weather;

dynamically selecting, by the at least one processor, a zone of influence for a sub-region of the geographic region based on weather conditions indicated by the weather data, the zone of influence defining a zone within the geographic region associated with a portion of the satellite image data and the weather data to be analyzed by the at least one processor for determining input variables derived from the satellite image data and the weather data to be used to calculate a forecast score for the sub-region;

analyzing, by the at least one processor, the portion of the satellite image data and the weather data within the dynamically-selected zone of influence to determine the input variables;

for at least the sub-region, applying weights to the input variables by the at least one processor according to the machine-learning algorithm;

mathematically combining the input variables by the processor according to the machine-learning algorithm thereby providing the forecast score indicating a probability or extent to which a weather event is forecast by the machine-learning algorithm to occur within the sub-region for a time period in the future; and

providing, by an output interface, an output based on the forecast score.

13. The method of claim 12, further comprising learning a regression equation by performing a regression analysis on a set of sample input variables derived from sample satellite image data and sample weather data, the regression equation including the weights, wherein the applying and the combining are preformed according to the regression equation.

14. The method of claim 12, wherein at least one of the input variables corresponds to a measurement for at least one pixel of the satellite image data.

15. The method of claim 12, wherein at least one of the input variables corresponds to at least one of the plurality of values of the weather data.

16. The method of claim 12, wherein the output defines a weather map for the geographic region.

17. The method of claim 12, further comprising storing, in memory, topographical data indicative of a topology of the geographic region, wherein at least one of the input variables is based on the topographical data.

18. The method of claim 12, further comprising:

calculating, by the at least one processor, a plurality of interest fields based on the satellite image data and the weather data, each of the interest fields indicative of weather occurring or forecast to occur in at least one sub-region of the geographic region; and

adjusting the zone of influence such that the zone of influence is larger for one of the interest fields relative to another of the interest fields.

19. The method of claim 12, further comprising:

calculating, by the at least one processor, at least one interest field based on the satellite image data and the weather data, the at least one interest field indicative of weather occurring or forecast to occur in at least one sub-region of the geographic region; and

controlling a size of the zone of influence based on the at least one interest field.

20. The method of claim 19, wherein the at least one interest field relates to wind measured or forecast in at least one sub-region of the geographic region.

21. The method of claim 12, further comprising:

associating the satellite image data and the weather data with a time period; and

adjusting a size of the zone of influence based on the time period that is associated with the satellite image data and the weather data.